Adversarial Cross-Domain Action Recognition with Co-Attention

Abstract

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.

arXiv commentAAAI 2020

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• The Kinetics Human Action Video Dataset
• Learning Transferable Features with Deep Adaptation Networks
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Dynamic Coattention Networks For Question Answering
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Action Recognition using Visual Attention
• Domain-Adversarial Training of Neural Networks
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation