Triadic temporal-semantic alignment for weakly-supervised video moment retrieval

Video Moment Retrieval (VMR) aims to identify specific event moments within untrimmed videos based on natural language queries. Existing VMR methods have been criticized for relying heavily on moment annotation bias rather than true multi-modal alignment reasoning. Weakly supervised VMR approaches i...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU, Jin, XIE, JiaLong, ZHOU, Fengyu, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9286
https://ink.library.smu.edu.sg/context/sis_research/article/10286/viewcontent/ssrn_4726553.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10286
record_format dspace
spelling sg-smu-ink.sis_research-102862024-09-13T14:38:04Z Triadic temporal-semantic alignment for weakly-supervised video moment retrieval LIU, Jin XIE, JiaLong ZHOU, Fengyu HE, Shengfeng Video Moment Retrieval (VMR) aims to identify specific event moments within untrimmed videos based on natural language queries. Existing VMR methods have been criticized for relying heavily on moment annotation bias rather than true multi-modal alignment reasoning. Weakly supervised VMR approaches inherently overcome this issue by training without precise temporal location information. However, they struggle with fine-grained semantic alignment and often yield multiple speculative predictions with prolonged video spans. In this paper, we take a step forward in the context of weakly supervised VMR by proposing a triadic temporalsemantic alignment model. Our proposed approach augments weak supervision by comprehensively addressing the multi-modal semantic alignment between query sentences and videos from both fine-grained and coarsegrained perspectives. To capture fine-grained cross-modal semantic correlations, we introduce a concept-aspect alignment strategy that leverages nouns to select relevant video clips. Additionally, an action-aspect alignment strategy with verbs is employed to capture temporal information. Furthermore, we propose an event-aspect alignment strategy that focuses on event information within coarse-grained video clips, thus mitigating the tendency towards long video span predictions during coarse-grained cross-modal semantic alignment. Extensive experiments conducted on the Charades-CD and ActivityNet-CD datasets demonstrate the superior performance of our proposed method. 2024-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9286 info:doi/10.1016/j.patcog.2024.110819 https://ink.library.smu.edu.sg/context/sis_research/article/10286/viewcontent/ssrn_4726553.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Weakly supervised learning Video moment retrieval Temporal-semantic alignment Graphics and Human Computer Interfaces Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Weakly supervised learning
Video moment retrieval
Temporal-semantic alignment
Graphics and Human Computer Interfaces
Software Engineering
spellingShingle Weakly supervised learning
Video moment retrieval
Temporal-semantic alignment
Graphics and Human Computer Interfaces
Software Engineering
LIU, Jin
XIE, JiaLong
ZHOU, Fengyu
HE, Shengfeng
Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
description Video Moment Retrieval (VMR) aims to identify specific event moments within untrimmed videos based on natural language queries. Existing VMR methods have been criticized for relying heavily on moment annotation bias rather than true multi-modal alignment reasoning. Weakly supervised VMR approaches inherently overcome this issue by training without precise temporal location information. However, they struggle with fine-grained semantic alignment and often yield multiple speculative predictions with prolonged video spans. In this paper, we take a step forward in the context of weakly supervised VMR by proposing a triadic temporalsemantic alignment model. Our proposed approach augments weak supervision by comprehensively addressing the multi-modal semantic alignment between query sentences and videos from both fine-grained and coarsegrained perspectives. To capture fine-grained cross-modal semantic correlations, we introduce a concept-aspect alignment strategy that leverages nouns to select relevant video clips. Additionally, an action-aspect alignment strategy with verbs is employed to capture temporal information. Furthermore, we propose an event-aspect alignment strategy that focuses on event information within coarse-grained video clips, thus mitigating the tendency towards long video span predictions during coarse-grained cross-modal semantic alignment. Extensive experiments conducted on the Charades-CD and ActivityNet-CD datasets demonstrate the superior performance of our proposed method.
format text
author LIU, Jin
XIE, JiaLong
ZHOU, Fengyu
HE, Shengfeng
author_facet LIU, Jin
XIE, JiaLong
ZHOU, Fengyu
HE, Shengfeng
author_sort LIU, Jin
title Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
title_short Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
title_full Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
title_fullStr Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
title_full_unstemmed Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
title_sort triadic temporal-semantic alignment for weakly-supervised video moment retrieval
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9286
https://ink.library.smu.edu.sg/context/sis_research/article/10286/viewcontent/ssrn_4726553.pdf
_version_ 1814047873083375616