Trajectory-Aligned Space-Time Tokens for Few-Shot Action Recognition

Abstract

We propose a simple yet effective approach for few-shot action recognition, emphasizing the disentanglement of motion and appearance representations. By harnessing recent progress in tracking, specifically point trajectories and self-supervised representation learning, we build trajectory-aligned tokens (TATs) that capture motion and appearance information. This approach significantly reduces the data requirements while retaining essential information. To process these representations, we use a Masked Space-time Transformer that effectively learns to aggregate information to facilitate few-shot action recognition. We demonstrate state-of-the-art results on few-shot action recognition across multiple datasets. Our project page is available here.

Cite

Text

Kumar et al. "Trajectory-Aligned Space-Time Tokens for Few-Shot Action Recognition." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72764-1_27

Markdown

[Kumar et al. "Trajectory-Aligned Space-Time Tokens for Few-Shot Action Recognition." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/kumar2024eccv-trajectoryaligned/) doi:10.1007/978-3-031-72764-1_27

BibTeX

@inproceedings{kumar2024eccv-trajectoryaligned,
  title     = {{Trajectory-Aligned Space-Time Tokens for Few-Shot Action Recognition}},
  author    = {Kumar, Pulkit and Padmanabhan, Namitha and Luo, Luke and Rambhatla, Sai Saketh and Shrivastava, Abhinav},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-72764-1_27},
  url       = {https://mlanthology.org/eccv/2024/kumar2024eccv-trajectoryaligned/}
}