title stringlengths 8 238 ⌀ | introduction stringlengths 10 3.28k | conclusion stringlengths 15 2.85k | prompt stringlengths 510 5.5k |
|---|---|---|---|
“Merging Results Is No Easy Task” : An International Survey Study of Collaborative Data Analysis Practices Among UX Practitioners | Usability testing is a frequently employed user-centred design method for detecting usability problems [ 25 , 110 ]. Despite being effective and useful, analyzing usability test sessions can be tedious, challenging, and time-consuming [ 12 , 25 , 29 , 81 ]. When analyzing usability test sessions, user experience (U... | We have conducted an international survey to understand the prac- tices and challenges of collaboration in the context of conducting data analysis on usability test sessions. Based on the responses of 279 participants who had varying UX experience and worked in different geographic locations, we found that UX practitio... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*“Merging Results Is No Easy Task” : An International Survey Study of Collaborative Data Analysis Practices Among UX Practitioners* and the introduction:Usability testing is a frequently employed user-centred design method ... |
Understanding Peer Review of Software Engineering Papers | You are invited to participate in a study entitled ”Identifying Best Practices in Peer Review” that is being conducted by Neil Ernst, Daniel Mendez, JeffCarver, and Marco Torchiano. | This study conducted an interview and survey-based study to understand some of the mechanisms by which reviewers in software engineering conduct reviews. We secured a large cohort of respondents derived from program committee mem- bers and journal reviewers of the past few years, many of whom have received recognition ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Understanding Peer Review of Software Engineering Papers* and the introduction:You are invited to participate in a study entitled ”Identifying Best Practices in Peer Review” that is being conducted by Neil Ernst, Daniel Me... |
Communication in Immersive Social Virtual Reality: A Systematic Review of 10 Years’ Studies | Communication is defined as the transmission of resources, such as knowledge, data, and skills, among different parties using shared symbols and media [ 12 , 62 ]. Efficient communication is an essential demand which would impact work efficiency and user experiences in contexts such as collaboration [ 64 ], social con... | Communication experiences and quality are crucial in social VR for collaboration and building social connectedness. We have con- ducted a systematic review using the PRISMA method to understand how communication has been studied in social VR in the past ten years’ published papers in the major digital libraries (i.e., ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Communication in Immersive Social Virtual Reality: A Systematic Review of 10 Years’ Studies* and the introduction:Communication is defined as the transmission of resources, such as knowledge, data, and skills, among differ... |
Deep Learning for Image Denoising: A Survey | Image processing has numerous applications including image segmentation [28], image classification [25,38,32,12], object detection [13], video tracking [36], im- age restoration [48] and action recognition [35]. Especially, the image denoising technology is one of the most important branches of image processing technolo... | This paper first comprehensively introduces the development of deep learning technologies on image processing applications. And then shows the implementa- tions of typical CNNs. After that, image denoising is illustrated in detail, which concludes the differences and ideas of different methods for image denoising in real ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Deep Learning for Image Denoising: A Survey* and the introduction:Image processing has numerous applications including image segmentation [28], image classification [25,38,32,12], object detection [13], video tracking [36],... |
Abstract | Outsourcing data storage to cloud-based services gains popularity among all kinds of users, as it seems to be a reasonable alternative to a private cloud. Cost aside, customers subordinate their choice of an adequate cloud provider to various factors, particularly availability, security, and privacy of the stored data. | In previous sections, we analyzed existing distributed storage systems provid- ing additional secrecy by use of fragmentation. We also presented database fragmentation solutions separating data in order to avoid full encryption. Few systems focus on providing a long term, secure and non-costly data storage. An- other m... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Abstract* and the introduction:Outsourcing data storage to cloud-based services gains popularity among all kinds of users, as it seems to be a reasonable alternative to a private cloud. Cost aside, customers subordinate th... |
Deep Long-Tailed Learning: A Survey | D EEP learning allows computational models, composed of multiple processing layers, to learn data representations with multiple levels of abstraction [1], [2] and has made incredible progress in computer vision [3], [4], [5], [6], [7], [8]. The key enablers of deep learning are the availability of large-scale datasets... | In this survey, we have extensively reviewed classic deep long- tailed learning methods proposed before mid-2021, according to the taxonomy of class re-balancing, information augmentation and module improvement. We have empirically analyzed several state-of-the-art long-tailed methods by evaluating to what extent they ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Deep Long-Tailed Learning: A Survey* and the introduction:D EEP learning allows computational models, composed of multiple processing layers, to learn data representations with multiple levels of abstraction [1], [2] and ... |
A Survey on Cross-Lingual Summarization | To help people efficiently grasp the gist of docu- ments in a foreign language, Cross-Lingual Sum- marization (XLS) aims to generate a summary in the target language from the given document(s) in a different source language. This task could be re- garded as a combination of monolingual summa- rization (MS) and machine t... | In this paper, we present the first comprehensive survey of current research efforts on XLS. We sys- tematically summarize existing XLS datasets and methods, highlight their characteristics and com- pare them with each other to provide deeper anal- yses. In addition, we give multiple perspective di- rections to facilita... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Cross-Lingual Summarization* and the introduction:To help people efficiently grasp the gist of docu- ments in a foreign language, Cross-Lingual Sum- marization (XLS) aims to generate a summary in the target lang... |
A Review of In-Memory Space-Efficient Data Structures for Temporal Graphs | Widespread adoption of complex network concepts in information technolo- gies has driven the creation of large volumes of data to be modelled as graphs. This increasing volume of data produced at high speeds brings us new chal- lenges. On one hand, we need efficient computational mechanisms to persist data that evolve co... | This paper reviewed studies about data structures for storing and querying temporal graphs in primary memory. We noted that many authors use data compression techniques to reduce the amount of space per contact needed to store temporal graphs. There are also succinct data structures that allows a variety of useful quer... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Review of In-Memory Space-Efficient Data Structures for Temporal Graphs* and the introduction:Widespread adoption of complex network concepts in information technolo- gies has driven the creation of large volumes of data t... |
A Comprehensive Survey on Networking over TV White Spaces | In a historic ruling in 2008, the Federal Communication Commission (FCC) in the United States opened up the TV white space spectrum for unlicensed secondary usage [1]. TV white spaces refer to the allocated but locally unused TV channels (between 54 MHz and 698 MHz in the US). Similar regulations have been adopted by ... | The 2008 FCC ruling in the United States on TV white space spectrum has opened up new opportunities for unlicensed operation in the TV band. TV white spaces’ availability, diverse bandwidth, and excellent propagational character- istics make them suitable for long range, low-power, and large area applications such as s... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Comprehensive Survey on Networking over TV White Spaces* and the introduction:In a historic ruling in 2008, the Federal Communication Commission (FCC) in the United States opened up the TV white space spectrum for unlice... |
Towards Evaluation of Autonomously Generated Musical Compositions: A Comprehensive Survey | The scope of algorithmic composition includes a wide range of tasks, which consist of the creation of melodies, chords, rhythms or even lyrics, i.e., all the typical components of music. The purpose of this work is to present the output of the neural network without any modifications. The aim of the research is not to r... | Although we have proposed several different methods of analytical, musicolog- ical and aesthetic evaluation, Matěj Kratochvíl’s rhetorical question from the introductory part of this paper (Kratochvíl 2020) was far from answered. Al- though the evaluation methods of musical metacreaction offer several possibili- ties by ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Towards Evaluation of Autonomously Generated Musical Compositions: A Comprehensive Survey* and the introduction:The scope of algorithmic composition includes a wide range of tasks, which consist of the creation of melodies... |
A Scoping Review of Publicly Available Language Tasks in Clinical Natural Language Processing | Since the inception of the first Integrating Biology and the Bedside (i2b2) shared task in 2006, currently known as the National Natural Language Processing (NLP) Clinical Challenge (n2c2), the field of clinical NLP has advanced in clinical applications that rely on text from the electronic health record (EHR). Tasks wit... | The interests in introducing and participating in clinical NLP tasks are growing with more tasks surfacing each year. The breadth of tasks is also growing with topics varying from tasks with specific clinical applications to those facil- itating clinical language understanding and reasoning. It is no doubt that the field... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Scoping Review of Publicly Available Language Tasks in Clinical Natural Language Processing* and the introduction:Since the inception of the first Integrating Biology and the Bedside (i2b2) shared task in 2006, currently ... |
A N E XTENSIVE R EVIEW OF C OMPUTATIONAL D ANCE A UTOMATION T ECHNIQUES AND A PPLICATIONS | Efforts of combining dance and computational power can be traced back to 1967. Being a domain that needs relatively more innovation and creativity than mere following standard procedures, dance was the slowest to adopt technology. The earliest attempt was published by A. Michael Noll [2] in Dance Magazine in 1967, alth... | Creativity is considered to be a gift and no two persons can be same in this process. A field of art like Dance is considered to be entirely a creative process although the basics are very clearly specified and taught in case of Classical Dance forms. Each choreographer is known for their particular style and creative fo... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A N E XTENSIVE R EVIEW OF C OMPUTATIONAL D ANCE A UTOMATION T ECHNIQUES AND A PPLICATIONS* and the introduction:Efforts of combining dance and computational power can be traced back to 1967. Being a domain that needs... |
T WENTY - TWO YEARS SINCE REVEALING CROSS - SITE SCRIPTING ATTACKS : A SYSTEMATIC MAPPING AND A COMPREHENSIVE SURVEY | The use of web applications through the Internet has become an indispensable mean for different business and governmental organizations to reduce costs, speed up activities, improve the quality of services and reach as many targeted people as possible. Users also get immense benefits from online provided services. Howev... | In this paper, we conducted a systematic mapping and a comprehensive survey studying the advancement in research to tackle XSS attacks. The study is not restricted to a period of time and covered high quality studies published since its discovery. Several studies were found in the literature but a remarkable interest i... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*T WENTY - TWO YEARS SINCE REVEALING CROSS - SITE SCRIPTING ATTACKS : A SYSTEMATIC MAPPING AND A COMPREHENSIVE SURVEY* and the introduction:The use of web applications through the Internet has become an indispensable mean ... |
A Deep Journey into Super-resolution: A Survey | ‘Everything has been said before, but since nobody listens we have to keep going back and beginning all over again.’ | Single-image super-resolution is a challenging research problem with important real-life applications. The phenom- enal success of deep learning approaches has resulted in rapid growth in deep convolutional network based tech- niques for image super-resolution. A diverse set of ap- proaches have been proposed with exci... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Deep Journey into Super-resolution: A Survey* and the introduction:‘Everything has been said before, but since nobody listens we have to keep going back and beginning all over again.’"},{"role":"assistant","content":"Con... |
Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey | Driven by the needs to protect the enormous value within data and the evolution of the emerging data mining techniques, information leakage becomes a growing concern for governments, organizations and individuals [ 3 ]. Compromising the confidentiality of protected information is an information leakage incident and a p... | In this survey, the ML-based stealing attack against the controlled information and the defense mechanisms are reviewed. The generalized MLBSA methodology compatible with the published work is outlined. Specifically, the MLBSA methodology uncovers how adversaries steal the controlled information in five phases, i.e. ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey* and the introduction:Driven by the needs to protect the enormous value within data and the evolution of the emerging data mining technique... |
Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey | Deep Learning is a subfield of Machine Learning (ML) that leverages the capabilities of artificial neural networks to automatically learn from data. These networks are fully-differentiable computational graphs optimized via gradient descent to learn representations from raw data [ 12 ], currently being the most efficie... | In this survey paper, we have investigated debiasing methods targeting fairness-aware neural networks for language and vision research. We have contextualized fairness and its relationship with biases and their possible origins. We have presented the main metrics and evaluation measures for assessing the level of fairn... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey* and the introduction:Deep Learning is a subfield of Machine Learning (ML) that leverages the capabilities of artificial neural networks ... |
D EEP N EURAL N ETWORKS FOR COVID-19 D ETECTION AND D IAGNOSIS USING I MAGES AND A COUSTIC - BASED T ECHNIQUES : A R ECENT R EVIEW | The novel severe acute respiratory syndrome-related coronavirus (SARS-CoV-2) started from Wuhan, China in December 2019 and spread to all the countries worldwide. This virus caused pneumonia of unknown cytology and is named COVID-19. This infectious disease has been classified as a public health crisis of the internatio... | Although the RT-PCR test is considered the gold standard for COVID-19 diagnosis, it is time-consuming to make a decision because of high false-negative levels in the results. Therefore, medical imaging modalities such as chest X-ray and chest CT scans are the best alternative according to scientists. Chest X-ray radiog... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*D EEP N EURAL N ETWORKS FOR COVID-19 D ETECTION AND D IAGNOSIS USING I MAGES AND A COUSTIC - BASED T ECHNIQUES : A R ECENT R EVIEW* and the introduction:The novel severe acute respiratory syndrome-related coronavirus... |
Anaphora and Coreference Resolution: A Review | A discourse is a collocated group of sentences which convey a clear understanding only when read together. The etymology of anaphora is ana (Greek for back) and pheri (Greek for to bear), which in simple terms means repetition. In computational linguistics, anaphora is typically defined as references to items mentio... | Our survey presents an exhaustive overview of the entity resolution field, which forms a core component of natural language processing research. In this survey, we put forth a detailed account of the types of references and the important constraints for entity resolution with the aim of establishing the bread scope of t... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Anaphora and Coreference Resolution: A Review* and the introduction:A discourse is a collocated group of sentences which convey a clear understanding only when read together. The etymology of anaphora is ana (Greek for b... |
Mining the online infosphere: A survey | Online infosphere 1 is the term corresponding to the Internet becoming a virtual parallel world formed from billions of networks of artificial life at different scales ranging from tiny pieces of software to massive AI tools running a factory or driving a car. The motivations for this are diverse, seeking to both hel... | In this survey we have presented a critical rundown on the evolution of the online infosphere by depicting some of the research areas that are becoming very crucial at current times. We started our discussion with a view of the infosphere as a collaborative platform, with a dedicated focus on Wikipedia. Wikipedia, th... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Mining the online infosphere: A survey* and the introduction:Online infosphere 1 is the term corresponding to the Internet becoming a virtual parallel world formed from billions of networks of artificial life at differen... |
Generalizing to Unseen Domains: A Survey on Domain Generalization | M ACHINE learning (ML) has achieved remarkable suc- cess in various areas, such as computer vision, natural language processing, and healthcare. The goal of ML is to design a model that can learn general and predictive knowledge from training data, and then apply the model to new (test) data. Traditional ML models are... | Generalization has always been an important research topic in machine learning research. In this article, we review the domain generalization areas by providing in-depth analysis of existing methods, datasets and applications. Then, we thoroughly analyze the methods. Based on our analysis, we provide several potential ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Generalizing to Unseen Domains: A Survey on Domain Generalization* and the introduction:M ACHINE learning (ML) has achieved remarkable suc- cess in various areas, such as computer vision, natural language processing, and ... |
How to Certify Machine Learning Based Safety-critical Systems? | Machine Learning (ML) is drastically changing the way we interact with the world. We are now using software applications powered by ML in critical as- pects of our daily lives; from finance, energy, to health and transportation. Thanks to frequent innovations in domains like Deep Learning (DL) and Re- inforcement Learni... | This paper provides a comprehensive overview of certification challenges for ML based safety-critical systems. We conducted a systematic review of the literature pertaining to Robustness , Uncertainty , Explainability , Verification , Safe Reinforcement Learning and Direct Certification . We identified gaps in this l... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*How to Certify Machine Learning Based Safety-critical Systems?* and the introduction:Machine Learning (ML) is drastically changing the way we interact with the world. We are now using software applications powered by ML in... |
Recommender Systems for the Internet of Things: A Survey | Recent advances in identification technologies, such as wireless sensor networks, RFID, and nan- otechnology, have empowered a multitude of phys- ical things with lifted computing ability [ 100 ]. Ev- eryday things have become recognizable, address- able, and controllable over the Internet. The poten- tial for seamlessl... | RSIoTs have become a crucial tool that can sup- port users in various decision-making activities. In this article, we have provided an extensive re- view of the most notable works to date on RSIoTs. We have proposed a classification framework of three categories for the organizing and dividing of existing publications a... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Recommender Systems for the Internet of Things: A Survey* and the introduction:Recent advances in identification technologies, such as wireless sensor networks, RFID, and nan- otechnology, have empowered a multitude of phys... |
Generative Adversarial Networks: A Survey Towards Private and Secure Applications | The technological breakthrough brought by Generative Adversarial Networks (GAN) has rapidly produced a revolutionary impact on machine learning and its related fields, and this impact has already flourished to various of research areas and applications. As a powerful generative framework, GAN has significantly promoted... | This survey intensively reviews the state-of-the-art approaches using GAN for privacy and security in a broad spectrum of applications, including image generation, video event detection, records publishing, distributed learning, malware detection, fraud detection, and so on. For the different purposes of attack and def... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Generative Adversarial Networks: A Survey Towards Private and Secure Applications* and the introduction:The technological breakthrough brought by Generative Adversarial Networks (GAN) has rapidly produced a revolutionary i... |
Multimodal Machine Learning: A Survey and Taxonomy | T HE world surrounding us involves multiple modalities — we see objects, hear sounds, feel texture, smell odors, and so on. In general terms, a modality refers to the way in which something happens or is experienced. Most people associate the word modality with the sensory modalities which represent our primary cha... | As part of this survey, we introduced a taxonomy of multi- modal machine learning: representation, translation, fusion, alignment, and co-learning. Some of them such as fusion have been studied for a long time, but more recent interest in representation and translation have led to a large number of new multimodal algor... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Multimodal Machine Learning: A Survey and Taxonomy* and the introduction:T HE world surrounding us involves multiple modalities — we see objects, hear sounds, feel texture, smell odors, and so on. In general terms, a mod... |
A Review on Facial Micro-Expressions Analysis: Datasets, Features and Metrics | F ACIAL expression research has a long history and accel- erated through the 1970s. The modern theory on basic emotions by Ekman et al [1], [2], [3] has generated more re- search than any other in the psychology of emotion [4]. They outline 7 universal facial expressions: happy, sad, anger, fear, surprise, disgust and... | We have presented a comprehensive review on datasets, features and metrics for micro-expressions analysis. The ultimate goal of this paper is to provide new insights and recommendations to advancing the micro-expression analysis research. We have provided a good guidelines for beginners and a detailed challenges and re... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Review on Facial Micro-Expressions Analysis: Datasets, Features and Metrics* and the introduction:F ACIAL expression research has a long history and accel- erated through the 1970s. The modern theory on basic emotions b... |
A Survey among Network Operators on BGP Prefix Hijacking | BGP prefix hijacking 101. Autonomous Systems (ASes) use the Border Gateway Protocol (BGP) [15] to advertise address space (as IPv4/IPv6 network prefixes) and establish inter-domain routes in the Internet. BGP is a distributed pro- tocol, lacking authentication of advertised routes. As a re- sult, an AS is able to advert... | In this work, to increase community understanding of ex- isting BGP hijacking defenses and the needs of network op- erators, we presented the results of a survey of 75 network operators around the world. | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey among Network Operators on BGP Prefix Hijacking* and the introduction:BGP prefix hijacking 101. Autonomous Systems (ASes) use the Border Gateway Protocol (BGP) [15] to advertise address space (as IPv4/IPv6 network... |
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey | D EEP L EARNING [1] is providing major breakthroughs in solving the problems that have withstood many attempts of machine learning and artificial intelligence com- munity in the past. As a result, it is currently being used to decipher hard scientific problems at an unprecedented scale, e.g. in reconstruction of brain ... | Deep learning is at the heart of the current rise of ma- chine learning and artificial intelligence. In the field of Computer Vision, it has become the work horse for appli- cations ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey* and the introduction:D EEP L EARNING [1] is providing major breakthroughs in solving the problems that have withstood many attempts of machine ... |
A Review of Anonymization for Healthcare Data Iyiola E. Olatunji ∗ , Jens Rauch 2 , Matthias Katzensteiner 3 , and Megha Khosla 1 | With the increasing adoption of healthcare information technology (HIT) by medical institutions, the generation and capture of healthcare-related data have been increasing rapidly in the past years. The application of artificial intelligence (AI) techniques already gives a glimpse of potential improvements ranging from ... | In this paper, we provided a comprehensive review of anonymization models and techniques applicable for relational and graph-based health care data. Besides, we studied possible attacks on anonymized data and empirically demonstrated reconstruction attack on MIMIC-III data. Finally we discussed existing defense mechani... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Review of Anonymization for Healthcare Data Iyiola E. Olatunji ∗ , Jens Rauch 2 , Matthias Katzensteiner 3 , and Megha Khosla 1* and the introduction:With the increasing adoption of healthcare information technol... |
A S URVEY AND I MPLEMENTATION OF P ERFORMANCE M ETRICS FOR S ELF -O RGANIZED M APS | Self-Organizing Maps (SOM) [ 1 ] have been used for almost 40 years across various application domains such as biology, geology, healthcare, industry [ 2 , 3 ] and humanities [ 4 ] as an interpretable tool to explore, cluster and visualize high-dimensional data sets. In every application, practitioners need to know wh... | In this paper, we reviewed various internal and external performance metrics for SOM and introduced the SOMperf Python module, enabling practitioners to easily evaluate their models. Future work perspectives include the computation of per-unit metrics, a SOM visualization module, as well as distance functions between s... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A S URVEY AND I MPLEMENTATION OF P ERFORMANCE M ETRICS FOR S ELF -O RGANIZED M APS* and the introduction:Self-Organizing Maps (SOM) [ 1 ] have been used for almost 40 years across various application domains such as b... |
Meta-Learning in Neural Networks: A Survey | Contemporary machine learning models are typically trained from scratch for a specific task using a fixed learn- ing algorithm designed by hand. Deep learning-based ap- proaches have seen great successes in a variety of fields [1]–[3]. However there are clear limitations [4]. For example, successes have largely been in ar... | The field of meta-learning has recently seen a rapid growth in interest. This has come with some level of confusion, with regards to how it relates to neighbouring fields, what it can be applied to, and how it can be benchmarked. In this survey we have sought to clarify these issues by thoroughly surveying the area both ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Meta-Learning in Neural Networks: A Survey* and the introduction:Contemporary machine learning models are typically trained from scratch for a specific task using a fixed learn- ing algorithm designed by hand. Deep learning-... |
An Overview of Distant Supervision for Relation Extraction with a Focus on Denoising and Pre-training Methods | Relation extraction (RE), a subtask of information extraction, is a foundational task in natural lan- guage processing (NLP). The RE task is to deter- mine a relationship between two distinct entities from text, producing fact triples in the form [ head , relation , tail ] or, as referred to in some works, [ sub- ject... | In this survey, we reviewed the relation extraction task with a focus on distant supervision. We traced the history of RE methods by discussing exemplary works and highlighting shortcomings to contextual- ize progress. We noted the key differences between pattern-based methods, statistical-based methods, neural-based m... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*An Overview of Distant Supervision for Relation Extraction with a Focus on Denoising and Pre-training Methods* and the introduction:Relation extraction (RE), a subtask of information extraction, is a foundational task in n... |
Scene Flow Estimation: A Survey | Scene flow is a three-dimensional motion field of the surface in world space, or in other words, it shows the three-dimensional displacement vector of each surface point between two frames. As most computer vision issues are, scene flow estimation is essentially an ill-posed energy minimization problem with three unknowns... | This paper presents a comprehensive and up-to-date survey on both scene flow estimation methods and the evaluation methodologies for the first time after 17 years since scene flow was introduced. We have discussed most of the estimation methods so researchers could have a clear view of this field and get inspired for their... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Scene Flow Estimation: A Survey* and the introduction:Scene flow is a three-dimensional motion field of the surface in world space, or in other words, it shows the three-dimensional displacement vector of each surface point ... |
Few-shot Learning: A Survey | “Can machines think [ 121 ]? ” This is the question raised in Alan Turing’s seminal paper entitled | Few-Shot Learning (FSL) is an important machine learning problem to facilitate real artificial intelligence. In this survey, we provide a comprehensive and systematic review of FSL. We first formally define FSL, and discuss the relatedness and difference of FSL with respect to relevant learning problems such as semi-su... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Few-shot Learning: A Survey* and the introduction:“Can machines think [ 121 ]? ” This is the question raised in Alan Turing’s seminal paper entitled"},{"role":"assistant","content":"Conclusion: Few-Shot Learning (FSL) is a... |
A survey on haptic technologies for mobile augmented reality | AR and MAR have atracted interest from both industry and academia in the last decade. MAR enhances the real world of a mobile user with computer-generated virtual content. AR applications combine real and virtual objects in a physical environment, are interactive in real time and display an augmented view. Te advances ... | In this survey, we depict the state-of-the-art of several haptic devices and their capabilities as wearables in MAR ecosystem. Furthermore, we classify the haptic feedback devices by their sensory nature and their design characteristics, such as mid-air, and exoskeleton. We start with a brief description of the main fe... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A survey on haptic technologies for mobile augmented reality* and the introduction:AR and MAR have atracted interest from both industry and academia in the last decade. MAR enhances the real world of a mobile user with com... |
A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges | M ACHINE learning models commonly make the closed- set assumption, where the test data is drawn i.i.d from the same distribution as the training data. Yet in practice, all types of test input data—even those on which we have not trained the classifier—can be encountered. Unfortunately, models can assign misleading co... | In many applications, it is not feasible to model all kinds of classes occurring during testing; thus, scenarios existing in domains such as OOD detection, OSR, ND (one-class learning), and AD become ubiquitous. Up to this time, these domains, in spite of having the same intention and a large intersection, have been fo... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges* and the introduction:M ACHINE learning models commonly make the closed- set assumption, where the test dat... |
A Brief Survey on Deep Learning Based Data Hiding, Steganography and Watermarking | Seeing is not always believing, i . e . a natural-looking image can contain secret information that is invisible to the gen- eral public. Data hiding enables concealing a secret message within a transport medium, such as a digital image, and its essential property lies in im perce pti bil it y for achieving the fu... | Deep learning based data hiding has become an emerging field and is drawing increasing attention. Our work conducts a brief survey on this topic by first outlining three basic meta- architectures. We further discuss the challenges of deep hid- ing in various applications, such as steganography, light field messaging and w... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Brief Survey on Deep Learning Based Data Hiding, Steganography and Watermarking* and the introduction:Seeing is not always believing, i . e . a natural-looking image can contain secret information that is invisible to... |
A Comprehensive Survey on Automatic Knowledge Graph Construction | Knowledge graphs (KGs) provide well-organized human knowledge for applications like search engines [ 1 ], recommendation systems [ 2 ], and question answering [ 3 ]. | With this paper, we delivered a comprehensive survey on the topic of knowledge graph construction. Specifically, we reviewed the tasks, methods, challenges, and related resources used to construct, refine, and integrate KGs from various data types in different scenarios. To probe into the essential topics for the big d... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Comprehensive Survey on Automatic Knowledge Graph Construction* and the introduction:Knowledge graphs (KGs) provide well-organized human knowledge for applications like search engines [ 1 ], recommendation systems [ 2 ],... |
Using Meta-heuristics and Machine Learning for Software Optimization of Parallel Computing Systems: A Systematic Literature Review | Traditionally, parallel computing [69] systems have been used for scientific and technical com- puting. Usually scientific and engineering computational problems are complex and resource intensive. To e ffi ciently solve these problems, utilization of parallel computing systems that may comprise multiple processing units i... | In this article, we have conducted a systematic literature review that describes approaches that use machine learning and meta-heuristics for software optimization of parallel computing systems. We have classified approaches based on the software life-cycle activities at compile-time and run-time, including the code opt... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Using Meta-heuristics and Machine Learning for Software Optimization of Parallel Computing Systems: A Systematic Literature Review* and the introduction:Traditionally, parallel computing [69] systems have been used for sci... |
A Survey on Echo Chambers on Social Media: Description, Detection and Mitigation | Having access to verified and trusted information is cru- cial in the midst of the COVID-19 pandemic, one of the most significant health crises (Mallah et al. 2021) in recent history. Exposure to misinformation on social media has been linked to COVID-19 vaccine hesitancy (Loomba et al. 2021), the belief that 5G towers s... | While the emergence of echo chambers can seem to be an unstoppable wave, we must realize that there is hope for a better information ecosystem. We showed that echo cham- bers are largely a byproduct of recommender systems. As such, what has been manufactured by these systems can like- wise be deconstructed by these sys... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Echo Chambers on Social Media: Description, Detection and Mitigation* and the introduction:Having access to verified and trusted information is cru- cial in the midst of the COVID-19 pandemic, one of the most si... |
A Systematic Literature Review of Empiricism and Norms of Reporting in Computing Education Research Literature | From 2009 to 2015, the number of bachelor’s degrees in Computer Science increased by 74 percent, while overall growth across all fields of study only rose by 16 percent [ 50 ]. Taulbee’s 2019 [ 75 ] report shows an increase from a recent minimum of under 10,000 bachelor’s degrees conferred in 2009 to over 30,000 degrees... | Our research goal was to characterize the reporting of empiricism in Computing Education Re- search literature by identifying whether publications include content necessary for researchers to perform replications, meta-analyses, and theory building. This systematic literature review sum- marizes the type of papers and ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Systematic Literature Review of Empiricism and Norms of Reporting in Computing Education Research Literature* and the introduction:From 2009 to 2015, the number of bachelor’s degrees in Computer Science increased by 74 p... |
Did Chatbots Miss Their ’Apollo Moment’ ∗ ? A Survey of the Potential, Gaps and Lessons from Using Collaboration Assistants During COVID-19 | COVID-19 1 is a global pandemic which started in China in the winter of 2019 and has spread around the world with over 100 million cases and killing more than two million people by Feb 2021 [WHO, 2021]. As the disease has progressed, new hot spots of the disease have emerged first in South-East Asia, then Europe and t... | COVID19 caused a major disruption in the lives of people around the world and they were looking for help with deci- sions in all aspects of their lives. At this juncture, chatbots as the AI technology for providing personalized decision sup- port at scale, was most needed. In this paper, we reviewed the range of method... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Did Chatbots Miss Their ’Apollo Moment’ ∗ ? A Survey of the Potential, Gaps and Lessons from Using Collaboration Assistants During COVID-19* and the introduction:COVID-19 1 is a global pandemic which started in China in ... |
Domain Adaptation for Visual Applications: A Comprehensive Survey | While huge volumes of unlabeled data are generated and made available in many domains, the cost of acquiring data labels remains high. To overcome the burden of annotation, alternative solutions have been proposed in the literature in order to exploit available unlabeled data from the domain (referred to as semi-superv... | This paper attempted to provide an overview of different visual domain adaptation solutions, including shallow methods and more recent deep models. We grouped the methods both by their similarity concerning the prob- lem (homogeneous versus heterogeneous data, unsupervised versus semi-supervised scenario) and the solut... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Domain Adaptation for Visual Applications: A Comprehensive Survey* and the introduction:While huge volumes of unlabeled data are generated and made available in many domains, the cost of acquiring data labels remains high.... |
State Representation Learning for Control: An Overview | Robotics control and artificial intelligence (AI) in a broad perspective heavily rely on the availability of compact and expressive representations of the sensor data. Designing such representations has long been performed manually by the designer, but deep learning now provides a general framework to learn such represe... | We reviewed State Representation Learning algorithms that are designed to find a way to compress high-dimensional observations data into a low and meaningful dimensional space for controlled systems. These models only require observations made by the system, the actions performed and optionally the reward of an associat... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*State Representation Learning for Control: An Overview* and the introduction:Robotics control and artificial intelligence (AI) in a broad perspective heavily rely on the availability of compact and expressive representation... |
Meta Learning for Natural Language Processing: A Survey | Recently, deep learning (DL) based natural lan- guage processing (NLP) has been one of the re- search mainstreams and yields significant perfor- mance improvement in many NLP problems. How- ever, DL models are data-hungry. The downside limits such models’ application to different domains, languages, countries, or styles... | This paper investigates how meta-learning is used in NLP applications. We review the task construction settings (Section 3 ), the commonly used methods including learning to initialize, learning to compare and neural architecture search (Section 4 ), and high- light research directions that go beyond improving perfor... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Meta Learning for Natural Language Processing: A Survey* and the introduction:Recently, deep learning (DL) based natural lan- guage processing (NLP) has been one of the re- search mainstreams and yields significant perfor- ... |
A N O PEN R EVIEW OF O PEN R EVIEW : A C RITICAL A NALYSIS OF THE M ACHINE L EARNING C ONFERENCE R EVIEW P ROCESS | Over the last decade, mainstream machine learning conferences have been strained by a deluge of conference paper submissions. At ICLR, for example, the number of submissions has grown by an order of magnitude within the last 5 years alone. Furthermore, the influx of researchers from disparate fields has led to a diverse ... | We find the level of reproducibility at ICLR (66% in 2020) to be higher than we expect when considering the much lower acceptance rate (26.5%), which seemingly contradicts the notion that reviews are “random.” Nonetheless, many authors find large swings in reviews as they resubmit papers to different conferences and find ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A N O PEN R EVIEW OF O PEN R EVIEW : A C RITICAL A NALYSIS OF THE M ACHINE L EARNING C ONFERENCE R EVIEW P ROCESS* and the introduction:Over the last decade, mainstream machine learning conferences have been straine... |
Deep Learning for Iris Recognition: A Review | Biological patterns, such as the face, voice, fingerprint, iris, and finger vein, have replaced traditional methods like keys, passwords, and access cards as the most reliable and effective human identification. Biological patterns, includ- ing face, voice, fingerprint, iris, and finger vein, are widely used for personal ide... | This paper provides a comprehensive review of deep learning-based IR, bridg- ing the lack of a comprehensive review related to deep learning in the field of IR. A total of 120 papers have been collected to support this work. The pur- pose of this paper is to discuss deep learning-based IR tasks. The paper begins with so... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Deep Learning for Iris Recognition: A Review* and the introduction:Biological patterns, such as the face, voice, fingerprint, iris, and finger vein, have replaced traditional methods like keys, passwords, and access cards as... |
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts | T RADITIONAL machine learning methods assume that the training and test data are drawn independently and identically (i.i.d.) from the same distribution [ 1 ]. However, when the test distribution (target) differs from the training distribution (source), we face the problem of distribution shifts . Such a shift poses ... | Learning to adapt a pre-trained model to unlabeled data under distribution shifts is an emerging and critical problem in the field of machine learning. This survey provides a comprehensive review of four related topics: source-free domain adaptation, test-time batch adaptation, online test- time adaptation, and test-tim... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts* and the introduction:T RADITIONAL machine learning methods assume that the training and test data are drawn independently and identically (i.i.d.) ... |
A Survey on Medical Document Summarization | The internet has become a global phenomenon, connecting people all over the world and allowing for the exchange of information on a scale that was previously unimaginable. The rise of the internet and the corresponding digitization of many aspects of daily life has had a profound impact on society leading to informatio... | The internet has drastically changed the way medical documents are created and accessed. In the past, they were often handwritten which made them hard to share and find. Now, they are typically created electronically which makes them much easier to both access and share. The internet has also allowed medical profession... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Medical Document Summarization* and the introduction:The internet has become a global phenomenon, connecting people all over the world and allowing for the exchange of information on a scale that was previously... |
MAC Protocols for Wireless Mesh Networks with Multi-beam Antennas: A Survey ⋆ | Due to a growing popularity of wireless local access, there exists a high demand to improve network throughput and enhance energy efficiency in data transmission between terminal devices (e.g., mobile phones) and access points (or base stations). However, wireless local networks mainly focus on the single-hop transmissio... | In this paper, we presented a comprehensive survey of MAC protocols in the wireless mesh network using multi-beam antennas. Theoretically, the capacity of WLAN can be consider- ably boosted by the use of multi-beam smart antennas. However, if the designers directly apply IEEE 802.11 to a WLAN with multi-beam antennas, ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*MAC Protocols for Wireless Mesh Networks with Multi-beam Antennas: A Survey ⋆* and the introduction:Due to a growing popularity of wireless local access, there exists a high demand to improve network throughput and enhance... |
Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review | Cancer is a disease marked by a disordered growth of abnormal cells that may lead to death if not treated. Around 1.9 million people in the US are expected to be diagnosed with cancer in 2023. Cancer is the second most common reason for death in the US, and it is expected to cause 1,670 deaths per day in the US in 2023... | Research efforts in integrating data across a few modalities have already shown encouraging results. There is no unified framework available for scaling across all possible modalities of cancer. The convergence of individual methodologies and data across varying scales may hold vital clues in creating a unified view of th... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review* and the introduction:Cancer is a disease marked by a disordered growth of abnormal cells that may lead to death if not treated. Around ... |
Vision-Centric BEV Perception: A Survey | A C curate and comprehensive understanding of surround- ing scenes, including dynamic objects and static streets, is essential for autonomous vehicles to make safe and effective driving decisions. 3D perception conducted in bird’s eye-view (BEV) has attracted immense attention in recent years for two main reasons. Firs... | This paper presents a comprehensive review of recent research on solving the view transformation between per- spective view and bird’s eye view. We introduce and discuss related methods by clearly classifying them according to the core idea and downstream vision tasks. To facilitate further research and implementation,... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Vision-Centric BEV Perception: A Survey* and the introduction:A C curate and comprehensive understanding of surround- ing scenes, including dynamic objects and static streets, is essential for autonomous vehicles to make s... |
Detection of Dangerous Events on Social Media: A Perspective Review | The extent of social media users consists of billions of people from all around the world. Initially, social media was developed with the object in mind to help connect with family and friends online. It was used to share everyday things, events, interests, and news within closed circles of family and friends. These we... | In this work, we laid the basis of the term “Dangerous Events” and explored different existing techniques and methods for detecting events on social media. Dangerous events contain a broad meaning, but we keep it essential to define the term better. We believe much more can be included in dangerous events, as we explored... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Detection of Dangerous Events on Social Media: A Perspective Review* and the introduction:The extent of social media users consists of billions of people from all around the world. Initially, social media was developed wit... |
Temporal Link Prediction: A Unified Framework, Taxonomy, and Review | For various complex systems (e.g., social networks, biology networks, and communication networks), graphs provide a generic abstraction to describe system entities and their relationships. For instance, one can abstract each entity as a node (vertex) and represent the relationship between a pair of entities as an edge ... | In this survey, we comprehensively reviewed existing representative TLP methods. We first gave the formal definitions regarding (i) data models of dynamic graphs (i.e., evenly-spaced snapshot sequence and unevenly-spaced edge sequence descriptions), (ii) task settings of TLP (i.e., level-1 and -2), and (iii) learning ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Temporal Link Prediction: A Unified Framework, Taxonomy, and Review* and the introduction:For various complex systems (e.g., social networks, biology networks, and communication networks), graphs provide a generic abstract... |
Deep Learning for Omnidirectional Vision: A Survey and New Perspectives | W ITH the rapid development of 3D technology and the pursuit of realistic visual experience, research interest in computer vision has gradually shifted from traditional 2D planar image data to omnidirectional image (ODI) data, also known as the 360 ˝ image, panoramic image, or spherical image data. ODI data captured... | In this survey, we comprehensively reviewed and analyzed the recent progress of DL methods for omnidirectional vision. We first introduced the principle of omnidirectional imaging, con- volution methods and datasets. We then provided a hierarchical and structural taxonomy of the DL methods. For each task in the taxonomy... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Deep Learning for Omnidirectional Vision: A Survey and New Perspectives* and the introduction:W ITH the rapid development of 3D technology and the pursuit of realistic visual experience, research interest in computer visi... |
How to Evaluate Your Dialogue Models: A Review of Approaches | Automatic evaluation is a non-trivial and challenging task in many sub-fields of natural language processing, e.g. text summarization [33], machine trans- lation [44,34] and dialogue system [37]. Especially, the evaluation of dialogue system often poorly correlates with human judgement. This mismatch is a key bottleneck... | In this paper, we summarize the evaluation methods of dialogue systems and a method-based taxonomy of the existing evaluation metric is attempted here. Even though much work has done to construct an effective evaluation method, it is still a challenging and understudied work to capture all aspects of dialogue response f... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*How to Evaluate Your Dialogue Models: A Review of Approaches* and the introduction:Automatic evaluation is a non-trivial and challenging task in many sub-fields of natural language processing, e.g. text summarization [33], ... |
Stochastic Process Semantics for Dynamical Grammar Syntax: An Overview | Probabilistic models of application domains are central to pattern recognition, machine learning, and scientific mod- eling in various fields. Consequently, unifying frameworks are likely to be fruitful for one or more of these fields. There are also more technical motivations for pursuing the unification of diverse model ... | We have established a syntax and semantics for a probabilistic modeling language based on independent processes leading to events linked by a shared set of objects. The semantics is based on a polynomial ring of time-evolution operators. The syntax is in the form of a set of rewrite rules. Stochastic Parameterized Gram... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Stochastic Process Semantics for Dynamical Grammar Syntax: An Overview* and the introduction:Probabilistic models of application domains are central to pattern recognition, machine learning, and scientific mod- eling in var... |
A S URVEY FOR R EAL -T IME N ETWORK P ERFORMANCE M EASUREMENT VIA M ACHINE L EARNING | # 1.1 Motivation | The real-time network is required for next-generation communication. To achieve the stringent goals of real-time network, network operators rely on an efficient, reliable, flexible, and globally network performance measurement, which helps to assist real-time networks in providing these services promptly. The complex mea... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A S URVEY FOR R EAL -T IME N ETWORK P ERFORMANCE M EASUREMENT VIA M ACHINE L EARNING* and the introduction:# 1.1 Motivation"},{"role":"assistant","content":"Conclusion: The real-time network is required for next-gener... |
All One Needs to Know about Priors for Deep Image Restoration and Enhancement: A Survey | I MAGE quality often deteriorates during capture, storage, trans- mission, and rendering. Typical degradations include blur, res- olution degradation, noise, and other artifacts. Image restoration and enhancement is a process that attempts to improve the image quality by removing these degradations while preserving th... | In this paper, we offered an insightful and methodical analysis of the recent advances of prior in deep image restoration and en- hancement. We conducted a hierarchical and structural taxonomy of prior commonly used in the DL-based methods. Meanwhile, we provided an insightful discussion on each prior regarding its pri... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*All One Needs to Know about Priors for Deep Image Restoration and Enhancement: A Survey* and the introduction:I MAGE quality often deteriorates during capture, storage, trans- mission, and rendering. Typical degradations ... |
A Systematic Literature Review on the security of Unmanned Aerial Vehicle System | The Unmanned Aerial Vehicle is an acronym for UAV, an air vehicle without any onboard pilot. The aircraft is controlled remotely by a controller which is on the ground or the UAV can fly autonomously with the complex pre-programmed model [ 1 ]. It is also called a Remotely Piloted Vehicle (RPV) when pilotless aircraft a... | This study has uncovered previous studies that examine how Unmanned Aerial Vehicle solutions might exacerbate cyber security issues. This study examined a UAV system’s overall security hazard. The thorough threat analysis of the system is intended to assist both the system’s designers and users in recognizing potential... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Systematic Literature Review on the security of Unmanned Aerial Vehicle System* and the introduction:The Unmanned Aerial Vehicle is an acronym for UAV, an air vehicle without any onboard pilot. The aircraft is controlled... |
Orchestrating Development Lifecycle of Machine Learning Based IoT Applications: A Survey | Rapid development of hardware, software and communication technologies boosts the speed of connecting the physical world to the Internet via Internet of Things (IoT). A report 1 shows that about 75.44 billion IoT devices will be connected to the Internet by 2025. These massive devices generate a large amount of dat... | Growing numbers of internet-connected things (IoT) produce vast amounts of data, build applications and provide various services in domains such as smart cities, energy, mobility, and smart transportation. ML is becoming a preliminary technique for analyzing IoT data. It produces high-level abstraction and insight that... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Orchestrating Development Lifecycle of Machine Learning Based IoT Applications: A Survey* and the introduction:Rapid development of hardware, software and communication technologies boosts the speed of connecting the physi... |
Conversational Agents in Therapeutic Interventions for Neuro developmental Disorders: A Survey | Neuro developmental Disorders (NDD) are a group of conditions that originate during childhood and are characterized by severe deficits in the cognitive and social areas [ 5 ]. NDD is a chronic state, but early and focused interventions are thought to mitigate its effects [ 22 ]. Traditional therapy involves different ... | The adoption of conversational agents for people with NDD is emerging as promising to assess and stimulate their skills in therapeutic interventions. This survey of a number of relevant publications in the last decade highlighted i) the large amount and variety of therapeutic goals addressed by the conversational agent... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Conversational Agents in Therapeutic Interventions for Neuro developmental Disorders: A Survey* and the introduction:Neuro developmental Disorders (NDD) are a group of conditions that originate during childhood and are ch... |
Self-Control in Cyberspace: Applying Dual Systems Theory to a Review of Digital Self-Control Tools | Smartphones and laptops give their users access to an aston- ishing range of tasks anywhere, anytime. While this provides innumerable benefits, a growing amount of public discus- sion and research attention focuses on a perhaps unexpected downside [ 7 , 19 , 62 , 102 , 108 , 121 , 187 , 201 ]: Having immense amo... | The challenge of designing powerful, always-connected dig- ital devices that support self-control over their use, is impor- tant to address. This paper contributes to such efforts on two levels: (i) by providing the first comprehensive functionality analysis of current apps and browser extensions for digital self-contr... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Self-Control in Cyberspace: Applying Dual Systems Theory to a Review of Digital Self-Control Tools* and the introduction:Smartphones and laptops give their users access to an aston- ishing range of tasks anywhere, anytime.... |
Multi-Agent Model Predictive Control: A Survey | Already back in 1978, Sandell et al. [22] surveyed a wide range of alternative methods for decentralized control. They find that a good combination of engi- neering judgment and analysis can be used to define in a reasonable way an ad- hoc control structure for a dynamic system. They conclude that methodologies are nee... | In this report we have given an overview of recent literature on multi-agent MPC. We have identified common aspects in each of the reviewed papers. This has led to the identification of certain groups and attributes at a rather non-mathematical level. This allows us to identify directions for further research. Although s... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Multi-Agent Model Predictive Control: A Survey* and the introduction:Already back in 1978, Sandell et al. [22] surveyed a wide range of alternative methods for decentralized control. They find that a good combination of e... |
Deep Learning for Text Attribute Transfer: A Survey | Driven by fast evolving pretraining techniques over large-scale corpora, neural language gener- ation (NLG) has made tremendous achievements and it can now generate various kinds of amazing human-like text on demand, such as stories, songs, press releases, and technical manuals, to name a few ( Keskar et al. , 2019 ; ... | This article presents the first comprehensive sur- vey on text attribute transfer which aims to change one or more attributes of a text with the other in- formation remained the same. We review recent research efforts and develop classification schemes to organize the existing literature. We start from providing the task... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Deep Learning for Text Attribute Transfer: A Survey* and the introduction:Driven by fast evolving pretraining techniques over large-scale corpora, neural language gener- ation (NLG) has made tremendous achievements and it ... |
A Survey of Data Optimization for Problems in Computer Vision Datasets | Recently, deep learning has achieved impressive progress in computer vision [ 74 , 76 ]. The success of deep learning mainly owes to three points, namely advanced deep network architectures ( e.g., ResNet) [ 46 ], powerful computing devices ( e.g., GPUs), and large datasets with labels ( e.g., ImageNet) [ 26 ]. Amo... | Data optimization is a key technique for improving dataset quality and has received increasing attention in machine learning and deep learning. In this paper, for the first time, we summarize and analyze inherent or extrinsic problems faced by large scale datasets. In response to these problems, we review the field of ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey of Data Optimization for Problems in Computer Vision Datasets* and the introduction:Recently, deep learning has achieved impressive progress in computer vision [ 74 , 76 ]. The success of deep learning mainly owe... |
MATH-AWARE SEARCH ENGINES: PHYSICS APPLICATIONS AND OVERVIEW | What do the AdS/CFT Correspondence, dumb holes, and effective theories have in common? | New research methods are enabled by equation-based search engines. From the simple benefit of looking up a concept by its equation - whether half-remembered or fully - to the advanced application of helping researchers discover new interdisciplinary connections, the possible applications elucidated so far have likely ba... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*MATH-AWARE SEARCH ENGINES: PHYSICS APPLICATIONS AND OVERVIEW* and the introduction:What do the AdS/CFT Correspondence, dumb holes, and effective theories have in common?"},{"role":"assistant","content":"Conclusion: New rese... |
Aesthetics, Personalization and Recommendation: A survey on Deep Learning in Fashion | If we go over the past decade and see how deep learning has achieved significant success in many popular Industries and areas. We observe how perception tasks, including visual object recognition and text understanding and speech recognition, have revolutionized different regions. There is no comparison as to how succe... | As the advancements in deep learning, CV and AI are getting stronger day by day their usage in the fashion industry has also become a very popular topic. From product personalization or better designing there are multiple ways in which AI and machine learning Technologies are impacting the global fashion industry and t... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Aesthetics, Personalization and Recommendation: A survey on Deep Learning in Fashion* and the introduction:If we go over the past decade and see how deep learning has achieved significant success in many popular Industries... |
DaRE: A Cross-Domain Recommender System with Domain-aware Feature Extraction and Review Encoder | With the rapid growth of e-commerce, recommender systems have become an obligatory tool for interconnecting customers with rele- vant items. Early schemes suffer from the cold-start problem caused by data insufficiency. To tackle the problems, some of them exploit auxiliary information such as social relations [ 12 ], ... | In this paper, we propose DaRE, a novel domain adaptation method utilizing review texts from multiple domains for a knowledge trans- fer. Compared to previous approaches, our method is able to capture domain-invariant and domain-specific information of different cat- egories with the aid of domain-aware feature extract... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*DaRE: A Cross-Domain Recommender System with Domain-aware Feature Extraction and Review Encoder* and the introduction:With the rapid growth of e-commerce, recommender systems have become an obligatory tool for interconnect... |
Empirical Review of Automated Analysis Tools on 47,587 Ethereum Smart Contracts | Blockchain technology has been receiving considerable attention from industry and academia, for it promises to disrupt the digital online world by enabling a democratic, open, and scalable digital economy based on decentralized distributed consensus without the intervention of third-party trusted authorities. Among the... | In this paper, we presented an empirical evaluation of 9 static anal- ysis tools on 69 annotated vulnerable contracts and on 47,518 con- tracts taken from the Ethereum’s network. The goal of this ex- periment was to obtain an overview of the current state of static analysis tools for Ethereum smart contracts. During th... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Empirical Review of Automated Analysis Tools on 47,587 Ethereum Smart Contracts* and the introduction:Blockchain technology has been receiving considerable attention from industry and academia, for it promises to disrupt t... |
Distributed Machine Learning on Mobile Devices: A Survey | Nowadays, machine learning, as well as deep learning, has become a hot topic and attracts great attention from both academia and industry. The core idea of machine learning is to use large amounts of data to fit a model that can generalize well to unseen inputs. As the increase of data size and model complexity, it bec... | In this survey paper, we have introduced the development of machine learning in recent years, from traditional machine learning to deep learning and followed by distributed machine learning and mobile learning. We have discussed their purposes and shown the necessity of mobile distributed machine learning in this infor... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Distributed Machine Learning on Mobile Devices: A Survey* and the introduction:Nowadays, machine learning, as well as deep learning, has become a hot topic and attracts great attention from both academia and industry. The ... |
An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos | Unsupervised representation learning has become an impor- tant domain with the advent of deep generative models which include the variational autoencoder (VAE), generative adver- sarial networks (GANs), Long Short Term memory networks (LSTMs), and others. Anomaly detection is a well known sub- domain of unsupervised le... | In this review paper we have focused on categorizing the dif- ferent unsupervised learning models for the task of anomaly detection in videos into three classes based on the prior information used to build the representations to characterize anomalies. | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos* and the introduction:Unsupervised representation learning has become an impor- tant domain with the advent of dee... |
Data-Driven Decision Making in COVID-19 Response: A Survey | The COVID-19 pandemic is an ongoing epidemic of the coronavirus disease [ 21 ]. The epidemic was declared a public health emergency of international concern by the World Health Organization (WHO) and it is impacting all aspects of life. At the same time, the COVID-19 epidemic is also generating a large amount of data t... | Data-driven decision making has been demonstrated to be both important and effective for the COVID-19 response. Different countries and regions have implemented many policies that are data-driven, such as prevention and control policies, psychological counselling policies, financial aid policies, and resumption/re- ope... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Data-Driven Decision Making in COVID-19 Response: A Survey* and the introduction:The COVID-19 pandemic is an ongoing epidemic of the coronavirus disease [ 21 ]. The epidemic was declared a public health emergency of intern... |
A Review of Machine Learning Applications in Fuzzing | Fuzzing is a technique in which a large number of gener- ated inputs, both valid and invalid, are fed into a program to search for flaws and vulnerabilities. Fuzzers, or automated tools to perform fuzzing, have played an important role in quality assurance, system administration, and vulnerabil- ity assessment over the... | In this survey, we discussed how machine learning (ML) has been applied to fuzzing. Because fuzzing problems lend them- selves more naturally to unsupervised and reinforcement learning techniques, supervised learning is rarely used to sup- port the fuzzing process. ML is most often used to support the Generate Inputs ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Review of Machine Learning Applications in Fuzzing* and the introduction:Fuzzing is a technique in which a large number of gener- ated inputs, both valid and invalid, are fed into a program to search for flaws and vulner... |
A Survey on Open Information Extraction | Information extraction (IE) turns the unstructured information expressed in natural language text into a structured representation (Jurafsky and Martin, 2009) in the form of relational tuples consisting of a set of arguments and a phrase denoting a semantic relation between them: ⟨ arg1 ; rel ; arg2 ⟩ . Traditional ... | We presented an overview of the various methods that were proposed to solve the task of Open IE. We classified them into the four categories of learning-based, rule-based, clause-based systems and ap- proaches capturing inter-proposition relationships, thereby showing their evolution over time, as well as the specific pr... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Open Information Extraction* and the introduction:Information extraction (IE) turns the unstructured information expressed in natural language text into a structured representation (Jurafsky and Martin, 2009) i... |
Software Testing Process Models Benefits & Drawbacks: a Systematic Literature Review | Software testing is a key phase of the software devel- opment process, as it represents the process of quality val- idation and verification of a software product [79]. Such phase is even more crucial nowadays, as software has be- come increasingly complex, mission-, safety- critical, and essential in daily activities, ... | Software testing is a key part of the software develop- ment process. The aim of this review was to provide an overview of existing software models that can be applied to improve the overall testing process. As the methodology for conducting the review, we used the Systematic Literature Review (SLR), to find empirical s... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Software Testing Process Models Benefits & Drawbacks: a Systematic Literature Review* and the introduction:Software testing is a key phase of the software devel- opment process, as it represents the process of quality val- ... |
An overview of gradient descent optimization algorithms ∗ | Gradient descent is one of the most popular algorithms to perform optimization and by far the most common way to optimize neural networks. At the same time, every state-of-the-art Deep Learning library contains implementations of various algorithms to optimize gradient descent (e.g. lasagne’s 2 , caffe’s 3 , and keras’... | In this blog post, we have initially looked at the three variants of gradient descent, among which mini-batch gradient descent is the most popular. We have then investigated algorithms that are most commonly used for optimizing SGD: Momentum, Nesterov accelerated gradient, Adagrad, Adadelta, RMSprop, Adam, as well as d... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*An overview of gradient descent optimization algorithms ∗* and the introduction:Gradient descent is one of the most popular algorithms to perform optimization and by far the most common way to optimize neural networks. At ... |
Interpretation of Black Box NLP Models: A Survey | Machine learning (ML) is now ubiquitous in the current era. Some of the ML models, especially deep learning-based models, achieve near-human accuracy. It has led to the adoption of ML into several areas, including critical areas like health, financial markets, criminal justice. ( Lipton , 2016 ). It had raised an impor... | This survey has presented an overview of inter- pretability methods from a causal and non-causal perspective. In this survey, we have presented a brief overview of the different approaches and some theoretical discussion around those methods. We have presented the representative paper exam- ples along with the specific ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Interpretation of Black Box NLP Models: A Survey* and the introduction:Machine learning (ML) is now ubiquitous in the current era. Some of the ML models, especially deep learning-based models, achieve near-human accuracy. ... |
A Survey on Dialogue Summarization: Recent Advances and New Frontiers | Dialogue summarization aims to distill the most important information from a dialogue into a shorter passage, which can help people quickly capture the highlights of a semi- structured and multi-participant dialogue without reviewing the complex dialogue context [Gurevych and Strube, 2004]. | This article presents the first comprehensive survey on the progress of dialogue summarization. We thoroughly summa- rize the existing works, highlight their challenges and provide leaderboards. Furthermore, we shed light on some new trends in this research field. We hope this survey can facilitate the research of the di... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Dialogue Summarization: Recent Advances and New Frontiers* and the introduction:Dialogue summarization aims to distill the most important information from a dialogue into a shorter passage, which can help peopl... |
Trust your neighbors: A comprehensive survey of neighborhood-based methods for recommender systems | The appearance and growth of online markets has had a considerable impact on the habits of consumers, providing them access to a greater variety of products and information on these goods. While this freedom of purchase has made online com- merce into a multi-billion dollar industry, it also made it more di ffi cult for ... | One of the earliest approaches proposed for the task item recommendation, neighbor- hood-based recommendation still ranks among the most popular methods for this problem. Although quite simple to describe and implement, this recommendation approach has several important advantages, including its ability to explain a re... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Trust your neighbors: A comprehensive survey of neighborhood-based methods for recommender systems* and the introduction:The appearance and growth of online markets has had a considerable impact on the habits of consumers,... |
Emotion in Reinforcement Learning Agents and Robots: A Survey. | This survey systematically covers the literature on computational models of emo- tion in reinforcement learning (RL) agents. Computational models of emotions are usually grounded in the agent decision-making architecture. In this work we focus on emotion models in a successful learning architecture: reinforcement learn... | This article surveyed emotion modelling in reinforcement learning (RL) agents. The literature has been structured according to the intrinsically motivated RL framework. We conclude by identifying the main benefits encountered in this work for the machine learning (ML), human-robot interaction (HRI), and affective mod- el... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Emotion in Reinforcement Learning Agents and Robots: A Survey.* and the introduction:This survey systematically covers the literature on computational models of emo- tion in reinforcement learning (RL) agents. Computationa... |
Handcrafted Feature Selection Techniques for Pattern Recognition: A Survey | In machine learning, representing and organizing data into meaningful information is a fundamental key that allows a classifier, such as neural networks, to determine the belongingness of observations into classes [1]. Observed data can be obtained from sources, in different domains, such as robot sensors, digital camer... | Feature selection and extraction is a way to reduce data dimensionality and facilitate the recognition of objects. Al- though all the feature selection methods aim in improving the identification of relevant data, they are applied in differ- ent ways, that may have a high or low cost depending on the problem. Filter a... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Handcrafted Feature Selection Techniques for Pattern Recognition: A Survey* and the introduction:In machine learning, representing and organizing data into meaningful information is a fundamental key that allows a classifie... |
A Survey on Anonymous Communication Systems with a Focus on Dining Cryptographers Networks | The continuously growing collection of data by pervasive computing techniques and great advances in com- munication during the current information age are bringing many benefits to society. This encompasses transformative changes and opportunities created in many aspects of daily life, e.g. healthcare, transporta- tion,... | Although data encryption algorithms protect the content of communications from unauthorised access, traffic analysis methods can be used to extract valuable information about communicating parties. Anonymous Communication Systems (ACSs) are able to additionally provide strong privacy properties like anonymity and ideally... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Anonymous Communication Systems with a Focus on Dining Cryptographers Networks* and the introduction:The continuously growing collection of data by pervasive computing techniques and great advances in com- muni... |
Learning to Communicate in Multi-Agent Reinforcement Learning : A Review | In recent years, Multi-Agent Reinforcement Learning has received a lot of interest, with more and more complex algorithms and structures improving the policy of multiple agents in more and more complex environments [1]. In Multi-agent settings, agents take actions and learn from their rewards simultaneously in the same... | We reviewed the main recent algorithms addressing the issue of communication and cooperation between multiple agents in a Reinforcement Learning environment. We also presented the current efforts in interpreting the language learned by these algorithms, and proposed a novel metric to evaluate the relevance of a generat... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Learning to Communicate in Multi-Agent Reinforcement Learning : A Review* and the introduction:In recent years, Multi-Agent Reinforcement Learning has received a lot of interest, with more and more complex algorithms and s... |
A Survey on Ransomware: Evolution, Taxonomy, and Defense Solutions | Recent years have witnessed a dramatic growth in the number of incidents a unique malware strain involved in, namely ransomware . This notorious malware strain has been targeting not only ordi- nary end users, but also governments and business organizations in almost any sector. Numerous incidents include Fortune 500 ... | In this paper, we provided a comprehensive survey of ransomware and ransomware defense re- search with respect to PCs/workstations, mobile devices and IoT/CPS environments. We presented a detailed overview on how ransomware evolved in time, thoroughly analyzed the key building blocks of ransomware, proposed a taxonomy ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Ransomware: Evolution, Taxonomy, and Defense Solutions* and the introduction:Recent years have witnessed a dramatic growth in the number of incidents a unique malware strain involved in, namely ransomware . Th... |
Deep Learning for Video-Text Retrieval: a Review | With the advent of the big data era, video media software ( e . g ., YouTuBe, TikTok, and Instagram) has become the main way for human beings to learn and entertain. Facing the explosive growth of multimedia information, people urgently need to find efficient ways to quickly search for an item that meets the user’s needs.... | In this survey, we have provided a comprehen- sive overview of deep learning methods for the video-text retrieval task. We have reviewed recent major advances on video-textual feature extraction, feature matching and objective functions, pre- sented their performance on publicly benchmarked datasets, and analyzed their... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Deep Learning for Video-Text Retrieval: a Review* and the introduction:With the advent of the big data era, video media software ( e . g ., YouTuBe, TikTok, and Instagram) has become the main way for human beings to learn ... |
A Survey on the Robustness of Feature Importance and Counterfactual Explanations | Machine learning (ML) models are being increasingly relied on to make decisions in a wide variety of contexts. Sometimes these deci- sions can have serious repercussions for individuals, with many ex- amples to be found in the health, legal or financial sectors (e.g., [4]). In such circumstances, explanations for a mode... | In this paper, we presented a review of existing approaches to anal- yse the robustness of two popular classes of post-hoc local ex- plainability methods - feature importance and counterfactual ex- planations. We defined robustness in the context of explainability and introduced a taxonomy to categorise existing approac... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on the Robustness of Feature Importance and Counterfactual Explanations* and the introduction:Machine learning (ML) models are being increasingly relied on to make decisions in a wide variety of contexts. Sometime... |
A R EVIEW OF V ISUAL O DOMETRY M ETHODS AND I TS A PPLICATIONS FOR A UTONOMOUS D RIVING | Autonomous driving has come a long way since it was first promoted in the DARPA Urban Challenge back in 2007. With major car manufacturers lobbying their technologies in autonomous driving, the ownership of autonomous vehicles is set to rise in the future. Current autonomous vehicles rely on a variety of sensors to achi... | The availability of recent works is greatly contributing towards the solution for the visual odometry problem. We have reviewed the various types of visual odometry methods in relation to their applications for autonomous driving. Both monocular and stereoscopic VO are viable approaches for autonomous driving, whereby ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A R EVIEW OF V ISUAL O DOMETRY M ETHODS AND I TS A PPLICATIONS FOR A UTONOMOUS D RIVING* and the introduction:Autonomous driving has come a long way since it was first promoted in the DARPA Urban Challenge back in 200... |
Analysis of the hands in egocentric vision: A survey | T HE hands are of primary importance for human beings, as they allow us to interact with objects and environments, com- municate with other people, and perform activities of daily living (ADLs) such as eating, bathing, and dressing. It is not a surprise that in individuals with impaired or reduced hand functionality (... | In this paper we showed how hand-related information can be retrieved and used in egocentric vision. We summarized the existing literature into three macro-areas, identifying the most prominent approaches for hand localization (e.g., hand detection, segmentation, pose estimation, etc.), interpretation (grasp analysis, ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Analysis of the hands in egocentric vision: A survey* and the introduction:T HE hands are of primary importance for human beings, as they allow us to interact with objects and environments, com- municate with other people... |
A RCHITECTURE AND S ECURITY OF SCADA S YSTEMS : A R EVIEW | Critical Infrastructures (CI) are often described as the infrastructures which provide essential services and serves as the foundation for any nation’s security, economy, and healthcare systems. Cyber-Physical Systems (CPS)/ Internet of Things (IoT), are supplementing traditional CI with data-rich operations. The list ... | SCADA systems have evolved into sophisticated complex open systems based on advanced technology systems connected to the Internet. This medium has lead the SCADA system vulnerable to attackers. Over the period, many attacks on SCADA industrial control system have been reported. The impact and severity of these attacks ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A RCHITECTURE AND S ECURITY OF SCADA S YSTEMS : A R EVIEW* and the introduction:Critical Infrastructures (CI) are often described as the infrastructures which provide essential services and serves as the foundation for a... |
System Log Parsing: A Survey | W ITH the proliferation of the Internet of Things (IoT), Cloud/Edge computing, Industry 4.0, and Fifth- generation mobile networks (5G), modern computing and communication systems commonly incorporate a large va- riety of (distributed) components to provide diversified services with guaranteed performance [1]. Conseque... | This paper aims at providing a comprehensive survey of log parsers. According to their log data classification and template extraction methods, we exhaustively investigate existing solutions and organize them in an easily-accessible taxonomy. Then we systematically analyze their perfor- mance metrics (accuracy and parsi... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*System Log Parsing: A Survey* and the introduction:W ITH the proliferation of the Internet of Things (IoT), Cloud/Edge computing, Industry 4.0, and Fifth- generation mobile networks (5G), modern computing and communicatio... |
A Survey on Natural Language Processing for Fake News Detection | Automatic fake news detection is the task of as- sessing the truthfulness of claims in news. This is a new, but critical NLP problem because both tra- ditional news media and social media have huge social-political impacts on every individual in the society. For example, exposure to fake news can cause attitudes of ine... | We described and compared previous datasets and proposed new requirements for future datasets; 1.Easy to make from raw data in internets, 2.Have enough classes of truthfulness, 3.Quote claims or articles from different speakers or publishers. Be- sides, We compared the accuracy of many previ- ous experiments and made s... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Natural Language Processing for Fake News Detection* and the introduction:Automatic fake news detection is the task of as- sessing the truthfulness of claims in news. This is a new, but critical NLP problem bec... |
Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey | The ability to understand user’s requests is essential to develop effective task-oriented dialogue systems. For example, in the utterance ” I want to listen to Hey Jude by The Beatles ”, a dialogue system should correctly identify that the user’s intention is to give a command to play a song, and that Hey Jude and Th... | We have surveyed recent neural-based models applied to SF and IC in the context of task-oriented di- alogue systems. We examined three approaches, i.e. independent , joint , and transfer learning based models. Joint models exploiting the relation between SF and IC simultaneously shown relatively bet- ter performance... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey* and the introduction:The ability to understand user’s requests is essential to develop effective task-oriented di... |
An introduction to optimization under uncertainty – A short survey | Optimization is a vast field and is arguably one of the most useful tools for scientists and engineers. With applications in almost any industry, from operations research to climate analysis to process control to robotics, the need to further our understanding of optimization and develop efficient algorithms to solve opti... | The field of optimization has made tremendous strides in progress over the last half-century. Theoretical de- velopments have improved our understanding of the structure of optimization problems. Advancements in computer technology continue to make optimization more applicable to everyday engineering. With the inclu- si... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*An introduction to optimization under uncertainty – A short survey* and the introduction:Optimization is a vast field and is arguably one of the most useful tools for scientists and engineers. With applications in almost an... |
Graph-based Knowledge Distillation: A survey and experimental evaluation | G RAPH data [ 1 ], which represents the relationship be- tween objects, is an important data type used in vari- ous real-world scenarios such as user recommendation [ 2 ], drug discovery [ 3 ], traffic forecasting [ 4 ], point cloud clas- sification [ 5 ], and chip design [ 6 ]. Unlike structured data in Euclidean space... | Based on the basic concept of graph data and knowledge distillation, the method of Graph-based Knowledge Distilla- tion is thoroughly combed in this paper. Firstly, on the basis of the design characteristics of the Graph-based Knowledge Distillation algorithm, it can be divided into three cate- gories: Graph-based Know... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Graph-based Knowledge Distillation: A survey and experimental evaluation* and the introduction:G RAPH data [ 1 ], which represents the relationship be- tween objects, is an important data type used in vari- ous real-world... |
Understand and Improve Contrastive Learning Methods for Visual Representation: A Review | Traditional supervised learning methods are hitting a bottleneck [ 33 ] because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks [ 17 , 51 , 33 ]. A promising alternative, self-supervised learning, as a type of ... | This review analyzed the key components in contrastive learning methods. First, we introduce that pretext invariant learning methods [ 35 ] outperform pretext covariant learning methods because the former preserves the mutual visual semantics under image transformation. After that, based on pretext invariant learning, ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Understand and Improve Contrastive Learning Methods for Visual Representation: A Review* and the introduction:Traditional supervised learning methods are hitting a bottleneck [ 33 ] because of their dependency on expensive... |
Towards Automatic Threat Detection: A Survey of Advances of Deep Learning within X-ray Security Imaging | X-ray security screening is one of the most widely used security measures for main- taining airport and transport security, whereby manual screening by human oper- ators plays the vital role. Despite the fact that experience and knowledge are the key factors for confident detection, external variables such as emotional ... | This paper taxonomises conventional machine and modern deep algorithms utilised within X-ray security imaging. Traditional approaches are sub-categorised based on computer vision tasks such as image enhancement, threat image projection, ob- ject segmentation, feature extraction, object classification, and detection. Rev... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Towards Automatic Threat Detection: A Survey of Advances of Deep Learning within X-ray Security Imaging* and the introduction:X-ray security screening is one of the most widely used security measures for main- taining airp... |
U NSUPERVISED R EPRESENTATION L EARNING IN D EEP R EINFORCEMENT L EARNING : A R EVIEW | Dynamic systems pervade our daily life. A pendulum swinging, a robot picking up objects, the flow of water in a river, the trend of economic costs, the spread of disease and the prediction of climate change are all examples of dynamic systems. Understanding how these systems evolve by discovering the governing equations... | This paper reviewed the most important and newest research trends on unsupervised SRL in DRL. From the literature, we identified four major classes of SRL methods: observation reconstruction, learning of latent MDP models, using priors, and contrastive learning. Moreover, we study how these methods are combined to devel... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*U NSUPERVISED R EPRESENTATION L EARNING IN D EEP R EINFORCEMENT L EARNING : A R EVIEW* and the introduction:Dynamic systems pervade our daily life. A pendulum swinging, a robot picking up objects, the flow of water in a... |
A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization | With the rapid development of the mobile internet, social media platforms and content sharing platforms are rapidly emerging. Compared with newspapers, radio, television, and other traditional media, mobile Internet-based media has faster speed, lower cost, and more diverse forms. Thus, the commercial social giants rep... | In this paper, we present a comprehensive survey on the IM problem from an ML-based com- binatorial optimization perspective. In order to compare ML-based algorithms with traditional approaches, we first summarize three kinds of traditional approaches: simulation-based, proxy- based, and sampling-based approaches, and ... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization* and the introduction:With the rapid development of the mobile internet, social media platforms and content sharing platforms are rapidly emer... |
Emotion Detection in Text: a Review | Emotion detection in computational linguistics is the process of identifying discrete emotion expressed in text. Emotion analysis can be viewed as a natural evolution of sentiment analysis and its more fine- grained model. However, as we observe in this paper, this field still has a long way to go before matching the suc... | In this paper, we reviewed the current state of emotion detection in textual data based on the available work in the literature. While many successful methodology and resources was introduces for sentiment analysis in recent years, researchers, by understanding the importance of more fine-grained affective information i... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*Emotion Detection in Text: a Review* and the introduction:Emotion detection in computational linguistics is the process of identifying discrete emotion expressed in text. Emotion analysis can be viewed as a natural evoluti... |
A Review of Intrusion Detection Systems and Their Evaluation in the IoT | An IDS is in essence a monitor placed on a device and/or network that analyses incoming messages, to detect attacks and/or unwanted traffic, and when paired with an intrusion prevention system can be used to stop attacks before they affect the system. They are trained using system behaviour data or from existing attack... | In this work we have extensively analysed and summarised the current state of the art in intrusion detection in the IoT. We have reviewed and summaries 51 proposed tools and technologies and characterised them. Our analysis has shown several new insights into how research in this field is developing, and potential gaps... | [{"role":"user", "content":"Help me to generate the conclusion of a survey paper given the title:*A Review of Intrusion Detection Systems and Their Evaluation in the IoT* and the introduction:An IDS is in essence a monitor placed on a device and/or network that analyses incoming messages, to detect attacks and/or unwan... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.