microsoft/xclip-base-patch16

1---2language: en3license: mit4tags:5- vision6- video-classification7model-index:8- name: nielsr/xclip-base-patch169  results:10  - task:11      type: video-classification12    dataset:13      name: Kinetics 40014      type: kinetics-40015    metrics:16    - type: top-1 accuracy17      value: 83.818    - type: top-5 accuracy19      value: 95.720---21 22# X-CLIP (base-sized model) 23 24X-CLIP model (base-sized, patch resolution of 16) 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 26This model was trained using 8 frames per video, at a resolution of 224x224.27 28Disclaimer: 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 description31 32X-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 36This 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 & limitations39 40You 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 for41fine-tuned versions on a task that interests you.42 43### How to use44 45For code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/xclip.html#).46 47## Training data48 49This model was trained on [Kinetics-400](https://www.deepmind.com/open-source/kinetics).50 51### Preprocessing52 53The exact details of preprocessing during training can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L247).54 55The exact details of preprocessing during validation can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L285).56 57During 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 results60 61This model achieves a top-1 accuracy of 83.8% and a top-5 accuracy of 95.7%.62