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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |
| Summary: | 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. |
|---|