Abstract
Given a text query, the task of Natural Language Video Localization (NLVL) is to localize a temporal moment in an untrimmed video that semantically matches the query. In this paper, we adopt a proposal-based solution that generates proposals (i.e. candidate moments) and then select the best matching proposal. On top of modeling the cross-modal interaction between candidate moments and the query, our proposed Moment Sampling DETR (MS-DETR) enables efficient moment-moment relation modeling. The core idea is to sample a subset of moments guided by the learnable templates with an adopted DETR framework. To achieve this, we design a multi-scale visual-linguistic encoder, and an anchor-guided moment decoder paired with a set of learnable templates. Experimental results on three public datasets demonstrate the superior performance of MS-DETR.- Anthology ID:
- 2023.acl-long.77
- 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:
- 1387–1400
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.77
- DOI:
- 10.18653/v1/2023.acl-long.77
- Cite (ACL):
- Wang Jing, Aixin Sun, Hao Zhang, and Xiaoli Li. 2023. MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1387–1400, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction (Jing et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.acl-long.77.pdf