README.md
2.7 KB · 62 lines · markdown Raw
1 ---
2 language: en
3 license: mit
4 tags:
5 - vision
6 - video-classification
7 model-index:
8 - name: nielsr/xclip-base-patch32
9 results:
10 - task:
11 type: video-classification
12 dataset:
13 name: Kinetics 400
14 type: kinetics-400
15 metrics:
16 - type: top-1 accuracy
17 value: 80.4
18 - type: top-5 accuracy
19 value: 95.0
20 ---
21
22 # X-CLIP (base-sized model)
23
24 X-CLIP model (base-sized, patch resolution of 32) trained fully-supervised on [Kinetics-400](https://www.deepmind.com/open-source/kinetics). It was introduced in the paper [Expanding Language-Image Pretrained Models for General Video Recognition](https://arxiv.org/abs/2208.02816) by Ni et al. and first released in [this repository](https://github.com/microsoft/VideoX/tree/master/X-CLIP).
25
26 This model was trained using 8 frames per video, at a resolution of 224x224.
27
28 Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
29
30 ## Model description
31
32 X-CLIP is a minimal extension of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
33
34 ![X-CLIP architecture](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/xclip_architecture.png)
35
36 This allows the model to be used for tasks like zero-shot, few-shot or fully supervised video classification and video-text retrieval.
37
38 ## Intended uses & limitations
39
40 You can use the raw model for determining how well text goes with a given video. See the [model hub](https://huggingface.co/models?search=microsoft/xclip) to look for
41 fine-tuned versions on a task that interests you.
42
43 ### How to use
44
45 For code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/xclip.html#).
46
47 ## Training data
48
49 This model was trained on [Kinetics-400](https://www.deepmind.com/open-source/kinetics).
50
51 ### Preprocessing
52
53 The exact details of preprocessing during training can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L247).
54
55 The exact details of preprocessing during validation can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L285).
56
57 During validation, one resizes the shorter edge of each frame, after which center cropping is performed to a fixed-size resolution (like 224x224). Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
58
59 ## Evaluation results
60
61 This model achieves a top-1 accuracy of 80.4% and a top-5 accuracy of 95.0%.
62