MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition
Paper • 2404.18327 • Published
Peihao Xiang
NoahMartinezXiang
AI & ML interests
My research focuses on the intersection of Computer Vision (Video Understanding), Deep Learning, Embedded Systems, and Multimodal Large Language Models (MLLMs), with an emphasis on real-time, resource-constrained, and wearable AI systems.
Recent Activity
authored a paper about 16 hours ago
MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition authored a paper about 16 hours ago
MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition authored a paper about 16 hours ago
Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker ClusteringOrganizations
None yet
authored 5
papers about 16 hours ago
MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition
Paper • 2412.18988 • Published
Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker Clustering
Paper • 2509.23358 • Published
Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers
Paper • 2602.03918 • Published
Real-Time Load Estimation for Load-lifting Exoskeletons Using Insole Pressure Sensors and Machine Learning
Paper • 2503.07527 • Published
updated a
dataset 8 days ago
published a
dataset 8 days ago
updated a
dataset 4 months ago
updated a
model 9 months ago
published a
model 9 months ago
[bot] Conversion to Parquet
#1 opened 12 months ago
by 
parquet-converter
updated a
model about 1 year ago
published a
model about 1 year ago
updated 2
models about 1 year ago
published 2
models about 1 year ago
updated 3
models about 1 year ago