metadata

license: cc-by-nc-4.0
tags:
  - vision
  - video-classification

TimeSformer (high-resolution variant, fine-tuned on Kinetics-400)

TimeSformer model pre-trained on Kinetics-400. It was introduced in the paper TimeSformer: Is Space-Time Attention All You Need for Video Understanding? by Tong et al. and first released in this repository.

Disclaimer: The team releasing TimeSformer did not write a model card for this model so this model card has been written by fcakyon.

Intended uses & limitations

You can use the raw model for video classification into one of the 400 possible Kinetics-400 labels.

How to use

Here is how to use this model to classify a video:

from transformers import TimesformerFeatureExtractor, TimesformerForVideoClassification
import numpy as np
import torch

video = list(np.random.randn(8, 3, 224, 224))

feature_extractor = TimesformerFeatureExtractor.from_pretrained("facebook/timesformer-hr-finetuned-k400")
model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-hr-finetuned-k400")

inputs = feature_extractor(video, return_tensors="pt")

with torch.no_grad():
  outputs = model(**inputs)
  logits = outputs.logits

predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

For more code examples, we refer to the documentation.

BibTeX entry and citation info

@inproceedings{bertasius2021space,
  title={Is Space-Time Attention All You Need for Video Understanding?},
  author={Bertasius, Gedas and Wang, Heng and Torresani, Lorenzo},
  booktitle={International Conference on Machine Learning},
  pages={813--824},
  year={2021},
  organization={PMLR}
}