SMS-Loss

This repository is for the Symmetric Multi-Similiarity Loss. A detailed instruction will be released soon.

Citation

The following paper reports the result of the SMS Loss. You could cite this paper if you find the repository is useful.

@misc{wang2024sms,
      title={Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024}, 
      author={Xiaoqi Wang and Yi Wang and Lap-Pui Chau},
      journal={arXiv preprint arXiv:2406.12256},
      year={2024}
}

Acknowledgements: this codebase borrows a lot from AVION; we thank the authors for releasing their code.