Local Correspondence Network for Weakly Supervised Temporal Sentence Grounding

Wenfei Yang, Tianzhu Zhang, Yongdong Zhang, Feng WuIEEE TIP 2021 · OpenReview

Abstract

Weakly supervised temporal sentence grounding has better scalability and practicability than fully supervised methods in real-world application scenarios. However, most of existing methods cannot model the fine-grained video-text local correspondences well and do not have effective supervision information for correspondence learning, thus yielding unsatisfying performance. To address the above issues, we propose an end-to-end Local Correspondence Network (LCNet) for weakly supervised temporal sentence grounding. The proposed LCNet enjoys several merits. First, we represent video and text features in a hierarchical manner to model the fine-grained video-text correspondences. Second, we design a self-supervised cycle-consistent loss as a learning guidance for video and text matching. To the best of our knowledge, this is the first work to fully explore the fine-grained correspondences between video and text for temporal sentence grounding by using self-supervised learning. Extensive experimental results on two benchmark datasets demonstrate that the proposed LCNet significantly outperforms existing weakly supervised methods.
BibTeX
@article{yang2021local,
  author = {Wenfei Yang and Tianzhu Zhang and Yongdong Zhang and Feng Wu},
  title = {{Local Correspondence Network for Weakly Supervised Temporal Sentence Grounding}},
  journal = {IEEE Trans. Image Process.},
  year = {2021},
  url = {https://openreview.net/forum?id=AKDEOyhcNf},
}

Loading related content...

Figure