EUVIMEDEUVIMED entdecken
Crossref

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

Bozheng Li, Mushui Liu, Gaoang Wang, Yunlong Yu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (17) · 18218-18226

DOI: 10.1609/aaai.v39i17.34004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Bozheng Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a novel Temporal Sequence-Aware-Model (TSAM) for few-shot action recognition (FSAR), which incorporates a sequential perceiver adapter into the pre-training framework, to integrate both the spatial information and the sequential temporal dynamics into the feature embeddings. Different from the existing fine-tuning approaches that capture temporal information by exploring the relationships among all the frames, our perceiver-based adapter recurrently captures the sequential dynamics alongside the timeline, which could perceive the frame order change. To obtain the discriminative representations for each class, we extend a textual corpus for each class derived from the large language models (LLMs) and enrich the visual prototypes by integrating the contextual semantic information. Besides, We introduce an unbalanced optimal transport strategy for feature matching that mitigates the impact of class-unrelated features, thereby facilitating more effective decision-making. Experimental results on five FSAR datasets demonstrate that our method establishes a new benchmark, outperforming the second-best competitors.

Zitieren

APA

Li, B., Liu, M., Wang, G., & Yu, Y. (2025). Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 39(17), 18218-18226. https://doi.org/10.1609/aaai.v39i17.34004

Vancouver

Li B, Liu M, Wang G, Yu Y. Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(17):18218-18226. doi:10.1609/aaai.v39i17.34004

BibTeX
@article{Li2025,
  author = {Li, Bozheng and Liu, Mushui and Wang, Gaoang and Yu, Yunlong},
  title = {Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {17},
  pages = {18218--18226},
  doi = {10.1609/aaai.v39i17.34004}
}
Kostenlos starten →