Skip to main navigation Skip to search Skip to main content

Boundary-Aware Temporal Sentence Grounding with Adaptive Proposal Refinement

  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Temporal sentence grounding (TSG) in videos aims to localize the temporal interval from an untrimmed video that is relevant to a given query sentence. In this paper, we introduce an effective proposal-based approach to solve the TSG problem. A Boundary-aware Feature Enhancement (BAFE) module is proposed to enhance the proposal feature with its boundary information, by imposing a new temporal difference loss. Meanwhile, we introduce a Boundary-aware Feature Aggregation (BAFA) module to aggregate boundary features and propose a Proposal-level Contrastive Learning (PCL) method to learn query-related content features by maximizing the mutual information between the query and proposals. Furthermore, we introduce a Proposal Interaction (PI) module with Adaptive Proposal Selection (APS) strategies to effectively refine proposal representations and make the final localization. Extensive experiments on Charades-STA, ActivityNet-Captions and TACoS datasets show the effectiveness of our solution. Our code is available at https://github.com/DJX1995/BAN-APR.

Original languageEnglish
Title of host publicationComputer Vision – ACCV 2022 - 16th Asian Conference on Computer Vision, Proceedings
EditorsLei Wang, Juergen Gall, Tat-Jun Chin, Imari Sato, Rama Chellappa
PublisherSpringer Science and Business Media Deutschland GmbH
Pages641-657
Number of pages17
ISBN (Print)9783031263156
DOIs
StatePublished - 2023
Event16th Asian Conference on Computer Vision, ACCV 2022 - Hybrid, Macao, China
Duration: Dec 4 2022Dec 8 2022

Publication series

NameLecture Notes in Computer Science
Volume13844 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference16th Asian Conference on Computer Vision, ACCV 2022
Country/TerritoryChina
CityHybrid, Macao
Period12/4/2212/8/22

Fingerprint

Dive into the research topics of 'Boundary-Aware Temporal Sentence Grounding with Adaptive Proposal Refinement'. Together they form a unique fingerprint.

Cite this