Pith. sign in

REVIEW 1 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.02025 v1 pith:KKD5HRO7 submitted 2023-07-05 cs.CV

Lin Sui , Fangzhou Mu , Yin Li This is my paper · ORCID
classification cs.CV
keywords challengeego4dmomentqueriesactionformersolutionsubmissionaction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives

    cs.CV 2025-02 conditional novelty 5.0 of 10

    Hier-EgoPack extends EgoPack's task-prototype transfer to multiple temporal granularities with a hierarchical GNN, improving Moment Queries and Long-Term Anticipation on Ego4D.

Pith tools