NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023

2023/07/05 by Sui Lin, Fangzhou Mu, Sui, Lin +3
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Multimodal Machine Learning Applications #Video Analysis and Summarization

paper · pdf · doi:10.48550/arxiv.2307.02025

openalex publication_date 2023/07/05 · openalex created_date 2023/07/07 · openalex updated_date 2026/07/28

Abstract

This report describes our submission to the Ego4D Moment Queries Challenge 2023. Our submission extends ActionFormer, a latest method for temporal action localization. Our extension combines an improved ground-truth assignment strategy during training and a refined version of SoftNMS at inference time. Our solution is ranked 2nd on the public leaderboard with 26.62% average mAP and 45.69% Recall@1x at tIoU=0.5 on the test set, significantly outperforming the strong baseline from 2023 challenge. Our code is available at https://github.com/happyharrycn/actionformer_release.

Related

• Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge
• A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge
• Action Sensitivity Learning for the Ego4D Episodic Memory Challenge 2023
• ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022
• Prompting Large Language Models to Reformulate Queries for Moment Localization