Proceedings

Learning Implicit Temporal Alignment for Few-shot Video Classification

Songyang Zhang, Jiale Zhou, Xuming He

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1309-1315.

https://doi.org/10.24963/ijcai.2021/181

Keywords

  • Computer Vision: Action Recognition
  • Machine Learning: Deep Learning

Abstract

Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations. To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization. Extensive experimental results on two challenging benchmarks, show that our method outperforms the prior arts with a sizable margin on Something-Something-V2 and competitive results on Kinetics.

Songyang Zhang, Jiale Zhou, and Xuming He. 2021. Learning Implicit Temporal Alignment for Few-shot Video Classification. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1309–1315. https://doi.org/10.24963/ijcai.2021/181
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards