This report presents ReLER submission to two tracks in the Ego4D Episodic Memory Benchmark in CVPR 2023, including Natural Language Queries and Moment Queries. This solution inherits from our proposed Action Sensitivity Learning framework (ASL) to better capture discrepant information of frames. Further, we incorporate a series of stronger video features and fusion strategies. Our method achieves an average mAP of 29.34, ranking 1st in Moment Queries Challenge, and garners 19.79 mean R1, ranking 2nd in Natural Language Queries Challenge. Our code will be released.
@article{arxiv.2306.09172,
title = {Action Sensitivity Learning for the Ego4D Episodic Memory Challenge 2023},
author = {Jiayi Shao and Xiaohan Wang and Ruijie Quan and Yi Yang},
journal= {arXiv preprint arXiv:2306.09172},
year = {2023}
}
Comments
Accepted to CVPR 2023 Ego4D Workshop; 1st in Ego4D Moment Queries Challenge; 2nd in Ego4D Natural Language Queries Challenge