EUVIMEDEUVIMED entdecken
Crossref

Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning

Kaibin Tian, Yanhua Cheng, Yi Liu, Xinglin Hou, Quan Chen, Han Li

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5207-5214

DOI: 10.1609/aaai.v38i6.28327 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Kaibin Tian und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, text-to-video retrieval methods based on CLIP have experienced rapid development. The primary direction of evolution is to exploit the much wider gamut of visual and textual cues to achieve alignment. Concretely, those methods with impressive performance often design a heavy fusion block for sentence (words)-video (frames) interaction, regardless of the prohibitive computation complexity. Nevertheless, these approaches are not optimal in terms of feature utilization and retrieval efficiency. To address this issue, we adopt multi-granularity visual feature learning, ensuring the model's comprehensiveness in capturing visual content features spanning from abstract to detailed levels during the training phase. To better leverage the multi-granularity features, we devise a two-stage retrieval architecture in the retrieval phase. This solution ingeniously balances the coarse and fine granularity of retrieval content. Moreover, it also strikes a harmonious equilibrium between retrieval effectiveness and efficiency. Specifically, in training phase, we design a parameter-free text-gated interaction block (TIB) for fine-grained video representation learning and embed an extra Pearson Constraint to optimize cross-modal representation learning. In retrieval phase, we use coarse-grained video representations for fast recall of top-k candidates, which are then reranked by fine-grained video representations. Extensive experiments on four benchmarks demonstrate the efficiency and effectiveness. Notably, our method achieves comparable performance with the current state-of-the-art methods while being nearly 50 times faster.

Zitieren

APA

Tian, K., Cheng, Y., Liu, Y., Hou, X., Chen, Q., & Li, H. (2024). Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5207-5214. https://doi.org/10.1609/aaai.v38i6.28327

Vancouver

Tian K, Cheng Y, Liu Y, Hou X, Chen Q, Li H. Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5207-5214. doi:10.1609/aaai.v38i6.28327

BibTeX
@article{Tian2024,
  author = {Tian, Kaibin and Cheng, Yanhua and Liu, Yi and Hou, Xinglin and Chen, Quan and Li, Han},
  title = {Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {6},
  pages = {5207--5214},
  doi = {10.1609/aaai.v38i6.28327}
}
Kostenlos starten →