Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding

Yuechen Wang, Wengang Zhou, Houqiang Li


Abstract
Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels,we are dedicated to the weakly supervised setting, where only video-level descriptions are provided for training. Most of the existing weakly supervised methods generate a candidate segment set and learn cross-modal alignment through a MIL-based framework. However, the temporal structure of the video as well as the complicated semantics in the sentence are lost during the learning. In this work, we propose a novel candidate-free framework: Fine-grained Semantic Alignment Network (FSAN), for weakly supervised TLG. Instead of view the sentence and candidate moments as a whole, FSAN learns token-by-clip cross-modal semantic alignment by an iterative cross-modal interaction module, generates a fine-grained cross-modal semantic alignment map, and performs grounding directly on top of the map. Extensive experiments are conducted on two widely-used benchmarks: ActivityNet-Captions, and DiDeMo, where our FSAN achieves state-of-the-art performance.
Anthology ID:
2021.findings-emnlp.9
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
89–99
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.9
DOI:
10.18653/v1/2021.findings-emnlp.9
Bibkey:
Cite (ACL):
Yuechen Wang, Wengang Zhou, and Houqiang Li. 2021. Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 89–99, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding (Wang et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.findings-emnlp.9.pdf
Data
ActivityNetActivityNet CaptionsDiDeMo