Refining Action Boundaries for One-stage Detection

Research output: Contribution to conferenceConference Paperpeer-review

Abstract

Current one-stage action detection methods, which simultaneously predict action boundaries and the corresponding class, do not estimate or use a measure of confidence in their boundary predictions, which can lead to inaccurate boundaries. We incorporate the estimation of boundary confidence into one-stage anchor-free detection, through an additional prediction head that predicts the refined boundaries with higher confidence. We obtain state-of-the-art performance on the challenging EPIC-KITCHENS-100 action detection as well as the standard THUMOS14 action detection benchmarks, and achieve improvement on the ActivityNet-1.3 benchmark.
Original languageEnglish
Number of pages8
Publication statusPublished - 25 Oct 2022
EventThe 18th IEEE Int. Conf. on Advanced Video and Signal-Based Surveillance -
Duration: 29 Nov 20222 Dec 2022

Conference

ConferenceThe 18th IEEE Int. Conf. on Advanced Video and Signal-Based Surveillance
Period29/11/222/12/22

Fingerprint

Dive into the research topics of 'Refining Action Boundaries for One-stage Detection'. Together they form a unique fingerprint.

Cite this