CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, W.k. Chan, Chong-Wah Ngo, Mike Zheng Shou, Nan Duan
Abstract
This paper tackles an emerging and challenging problem of long video temporal grounding (VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a query-guided window selection strategy to speed up inference, and (2) proposes a coarse-to-fine mechanism via a novel incorporation of contrastive learning to enhance multi-modal alignment for long videos. Extensive experiments on two large-scale long VTG benchmarks consistently show both substantial performance gains (e.g., from 3.13 to 6.87% on MAD) and state-of-the-art results. Analyses also reveal higher efficiency as the query-guided window selection mechanism accelerates inference time by 2x on Ego4D-NLQ and 15x on MAD while keeping SOTA results. Codes have been released at https://github.com/houzhijian/CONE.- Anthology ID:
- 2023.acl-long.445
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8013–8028
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.445
- DOI:
- 10.18653/v1/2023.acl-long.445
- Cite (ACL):
- Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, W.k. Chan, Chong-Wah Ngo, Mike Zheng Shou, and Nan Duan. 2023. CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8013–8028, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding (Hou et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2023.acl-long.445.pdf