EUVIMEDEUVIMED entdecken
Crossref

Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning

Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Liu Qin, Ziyao Chen, Qing Gu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 3113-3121

DOI: 10.1609/aaai.v39i3.32320 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Shiping Ge und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which simplifies the complex event proposal and localization process while maintaining effectiveness. Specifically, our model comprises two components: a dual-mode video captioning module and a mask generation module. The dual-mode video captioning module captures global event information and generates descriptive captions, while the mask generation module generates differentiable positive and negative masks for localizing the events. These masks enable the implicit alignment of event locations and captions by ensuring that captions generated from positively and negatively masked videos are complementary, thereby forming a complete video description. In this way, even under weak supervision, the event location and event caption can be aligned implicitly. Extensive experiments on the public datasets demonstrate that our method outperforms existing weakly-supervised methods and achieves competitive results compared to fully-supervised methods.

Zitieren

APA

Ge, S., Chen, Q., Jiang, Z., Yin, Y., Qin, L., Chen, Z., & Gu, Q. (2025). Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 3113-3121. https://doi.org/10.1609/aaai.v39i3.32320

Vancouver

Ge S, Chen Q, Jiang Z, Yin Y, Qin L, Chen Z, et al. Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):3113-3121. doi:10.1609/aaai.v39i3.32320

BibTeX
@article{Ge2025,
  author = {Ge, Shiping and Chen, Qiang and Jiang, Zhiwei and Yin, Yafeng and Qin, Liu and Chen, Ziyao and Gu, Qing},
  title = {Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {3113--3121},
  doi = {10.1609/aaai.v39i3.32320}
}
Kostenlos starten →