Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,54 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- AlexFierro9/Kinetics400
|
5 |
+
- imagenet-1k
|
6 |
+
- HuggingFaceM4/something_something_v2
|
7 |
+
language:
|
8 |
+
- en
|
9 |
+
pipeline_tag: video-classification
|
10 |
---
|
11 |
+
|
12 |
+
|
13 |
+
|
14 |
+
<br>
|
15 |
+
|
16 |
+
# VideoMamba
|
17 |
+
|
18 |
+
## Model Details
|
19 |
+
|
20 |
+
VideoMamba is a purely SSM-based model for video understanding.
|
21 |
+
|
22 |
+
- **Developed by:** [OpenGVLab](https://github.com/OpenGVLab)
|
23 |
+
- **Model type:** An efficient backbone based on the bidirectional state space model.
|
24 |
+
- **License:** Non-commercial license
|
25 |
+
|
26 |
+
|
27 |
+
### Model Sources
|
28 |
+
|
29 |
+
- **Repository:** https://github.com/OpenGVLab/VideoMamba
|
30 |
+
- **Paper:** https://arxiv.org/abs/2403.06977
|
31 |
+
|
32 |
+
## Uses
|
33 |
+
|
34 |
+
The primary use of VideoMamba is research on image and video tasks, e.g., image classification, action recognition, long-term video understanding, and video-text retrieval, with an SSM-based backbone.
|
35 |
+
The primary intended users of the model are researchers and hobbyists in computer vision, machine learning, and artificial intelligence.
|
36 |
+
|
37 |
+
## How to Get Started with the Model
|
38 |
+
|
39 |
+
- You can replace the backbone for video tasks with the proposed VideoMamba: https://github.com/OpenGVLab/VideoMamba/blob/main/videomamba/video_sm/models/videomamba.py
|
40 |
+
- Then you can load this checkpoint and start training.
|
41 |
+
|
42 |
+
|
43 |
+
### Citation Information
|
44 |
+
|
45 |
+
```
|
46 |
+
@misc{li2024videomamba,
|
47 |
+
title={VideoMamba: State Space Model for Efficient Video Understanding},
|
48 |
+
author={Kunchang Li and Xinhao Li and Yi Wang and Yinan He and Yali Wang and Limin Wang and Yu Qiao},
|
49 |
+
year={2024},
|
50 |
+
eprint={2403.06977},
|
51 |
+
archivePrefix={arXiv},
|
52 |
+
primaryClass={cs.CV}
|
53 |
+
}
|
54 |
+
```
|