Action Sensitivity Learning for the Ego4D Episodic Memory Challenge 2023

15 Jun 2023  ·  Jiayi Shao, Xiaohan Wang, Ruijie Quan, Yi Yang ·

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Moment Queries Ego4D ASL Avg mAP (0.1-0.5) 27.85 # 1
Recall 46.98 # 1

Methods


No methods listed for this paper. Add relevant methods here