README.md
1.4 KB · 39 lines · markdown Raw
1 ---
2 license: "mit"
3 tags:
4 - vision
5 - video-classification
6 ---
7
8 # ViViT (Video Vision Transformer)
9
10 ViViT model as introduced in the paper [ViViT: A Video Vision Transformer](https://arxiv.org/abs/2103.15691) by Arnab et al. and first released in [this repository](https://github.com/google-research/scenic/tree/main/scenic/projects/vivit).
11
12 Disclaimer: The team releasing ViViT did not write a model card for this model so this model card has been written by the Hugging Face team.
13
14 ## Model description
15
16 ViViT is an extension of the [Vision Transformer (ViT)](https://huggingface.co/docs/transformers/v4.27.0/model_doc/vit) to video.
17
18 We refer to the paper for details.
19
20 ## Intended uses & limitations
21
22 The model is mostly meant to intended to be fine-tuned on a downstream task, like video classification. See the [model hub](https://huggingface.co/models?filter=vivit) to look for fine-tuned versions on a task that interests you.
23
24 ### How to use
25
26 For code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/vivit).
27
28 ### BibTeX entry and citation info
29
30 ```bibtex
31 @misc{arnab2021vivit,
32 title={ViViT: A Video Vision Transformer},
33 author={Anurag Arnab and Mostafa Dehghani and Georg Heigold and Chen Sun and Mario Lučić and Cordelia Schmid},
34 year={2021},
35 eprint={2103.15691},
36 archivePrefix={arXiv},
37 primaryClass={cs.CV}
38 }
39 ```