Text Generation
Transformers
PyTorch
llava
Swindl commited on
Commit
86f6e73
·
verified ·
1 Parent(s): 4d5a19d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -11
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  license: apache-2.0
3
- pipeline_tag: video-segmentation
4
  library_name: transformers
5
  ---
6
 
@@ -22,11 +21,6 @@ library_name: transformers
22
  [![HuggingFace](https://img.shields.io/badge/HuggingFace-Model-yellow?style=flat&logo=HuggingFace&logoColor=yellow)](https://huggingface.co/Swindl/GLUS-A)
23
 
24
 
25
-
26
- <div align=center>
27
- <img src="assets/teaserfig.png" style="width:100%;">
28
- </div>
29
-
30
  ## Overview
31
 
32
  **RefVOS in complex scenarios** places high demands on models' video understanding and fine-grained localization capabilities. Recently, numerous models leveraging **MLLM-based** comprehension and reasoning abilities have been proposed to address this challenge. Our **GLUS** advances further along this methodological path.
@@ -37,11 +31,6 @@ library_name: transformers
37
 
38
  📌 **GLUS is simple.** It elegantly integrates the approach for complex-scenario RefVOS tasks within a single MLLM framework, eliminating the necessity of utilizing other independent modules.
39
 
40
- <div align=center>
41
- <img src="assets/pipeline_00.png" style="width:100%;">
42
- </div>
43
-
44
- ## News
45
 
46
  ## Installation
47
  ```shell
 
1
  ---
2
  license: apache-2.0
 
3
  library_name: transformers
4
  ---
5
 
 
21
  [![HuggingFace](https://img.shields.io/badge/HuggingFace-Model-yellow?style=flat&logo=HuggingFace&logoColor=yellow)](https://huggingface.co/Swindl/GLUS-A)
22
 
23
 
 
 
 
 
 
24
  ## Overview
25
 
26
  **RefVOS in complex scenarios** places high demands on models' video understanding and fine-grained localization capabilities. Recently, numerous models leveraging **MLLM-based** comprehension and reasoning abilities have been proposed to address this challenge. Our **GLUS** advances further along this methodological path.
 
31
 
32
  📌 **GLUS is simple.** It elegantly integrates the approach for complex-scenario RefVOS tasks within a single MLLM framework, eliminating the necessity of utilizing other independent modules.
33
 
 
 
 
 
 
34
 
35
  ## Installation
36
  ```shell