Adversarial Cross-Domain Action Recognition with Co-Attention


  • Boxiao Pan Stanford University
  • Zhangjie Cao Stanford University
  • Ehsan Adeli Stanford University
  • Juan Carlos Niebles Stanford University



Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos. However, the problem of cross-domain action recognition, where training and testing videos are drawn from different underlying distributions, remains largely under-explored. Previous methods directly employ techniques for cross-domain image recognition, which tend to suffer from the severe temporal misalignment problem. This paper proposes a Temporal Co-attention Network (TCoN), which matches the distributions of temporally aligned action features between source and target domains using a novel cross-domain co-attention mechanism. Experimental results on three cross-domain action recognition datasets demonstrate that TCoN improves both previous single-domain and cross-domain methods significantly under the cross-domain setting.




How to Cite

Pan, B., Cao, Z., Adeli, E., & Niebles, J. C. (2020). Adversarial Cross-Domain Action Recognition with Co-Attention. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11815-11822.



AAAI Technical Track: Vision