EUVIMEDEUVIMED entdecken
Crossref

Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition

Jiazheng Xing, Mengmeng Wang, Yong Liu, Boyu Mu

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3001-3009

DOI: 10.1609/aaai.v37i3.25403 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jiazheng Xing und 3 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the crucial low-level spatial features and short-term temporal relations. Actually, the former feature could bring rich local semantic information, and the latter feature could represent motion characteristics of adjacent frames, respectively. In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner. First, to exploit the low-level spatial features, we design a feature fusion architecture search module to automatically search for the best combination of the low-level and high-level spatial features. Next, inspired by the recent transformer, we introduce a long-term temporal modeling module to model the global temporal relations based on the extracted spatial appearance features. Meanwhile, we design another short-term temporal modeling module to encode the motion characteristics between adjacent frame representations. After that, the final predictions can be obtained by feeding the embedded rich spatial-temporal features to a common frame-level class prototype matcher. We extensively validate the proposed SloshNet on four few-shot action recognition datasets, including Something-Something V2, Kinetics, UCF101, and HMDB51. It achieves favorable results against state-of-the-art methods in all datasets.

Zitieren

APA

Xing, J., Wang, M., Liu, Y., & Mu, B. (2023). Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3001-3009. https://doi.org/10.1609/aaai.v37i3.25403

Vancouver

Xing J, Wang M, Liu Y, Mu B. Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3001-3009. doi:10.1609/aaai.v37i3.25403

BibTeX
@article{Xing2023,
  author = {Xing, Jiazheng and Wang, Mengmeng and Liu, Yong and Mu, Boyu},
  title = {Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {3},
  pages = {3001--3009},
  doi = {10.1609/aaai.v37i3.25403}
}
Kostenlos starten →