Add model card

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+pipeline_tag: video-classification
+tags:
+  - video
+  - action-recognition
+  - efficient-inference
+  - token-selection
+library_name: pytorch
+---
+
+# LookWhen ViT-B/16
+
+Pre-trained checkpoint for **"LookWhen? Fast Video Recognition by Learning When, Where,
+and What to Compute"** ([arXiv:2605.06809](https://arxiv.org/abs/2605.06809)).
+
+LookWhen splits video recognition in two: a shallow **selector** scores every patch of a
+2x-downscaled clip, and a deep **extractor** processes only the top-K of them while still
+predicting features of the whole video.
+
+This is the model used throughout the paper: ViT-B/16, pre-trained for 20 epochs on
+Kinetics-400 and SSv2 by distilling InternVideo2's video token and DINOv3's frame and
+patch tokens, with selection supervised by top1-distance token uniqueness. It was trained
+over sparsity 70-95%, so it runs anywhere in that range without retraining.
+
+## Usage
+
+```bash
+pip install git+https://github.com/alisalamatian1/LookWhen.git
+```
+
+```python
+import torch
+from lookwhen import LookWhen
+from lookwhen.data.video import load_clip
+
+model = LookWhen.from_pretrained().cuda().eval()   # downloads this checkpoint
+clip = load_clip("video.mp4", num_frames=16, img_size=224).unsqueeze(0).cuda()
+
+out = model(clip, keep_ratio=0.1)   # keep_ratio = 1 - sparsity
+out["video"]   # (1, 768) video embedding
+```
+
+Code, training, and evaluation: https://github.com/alisalamatian1/LookWhen
+
+## Citation
+
+```bibtex
+@article{salamatian2026lookwhen,
+  title   = {LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute},
+  author  = {Salamatian, Ali and Fuller, Anthony and Sarkar, Pritam and
+             Green, James R. and Sigal, Leonid and Shelhamer, Evan},
+  journal = {arXiv preprint arXiv:2605.06809},
+  year    = {2026}
+}
+```