Temporal Attentive Alignment for Video Domain Adaptation

2019/05/26 by Min-Hung Chen, Zsolt Kira, Chen, Min-Hung +3
Computer Science · #Domain Adaptation and Few-Shot Learning #Human Pose and Action Recognition #Multimodal Machine Learning Applications #cs.CV #cs.LG #cs.MM

paper · pdf · doi:10.48550/arxiv.1905.10861

CVPR2019 Workshop (Learning from Unlabeled Videos). Source code: http://github.com/cmhungsteve/TA3N

arxiv created 2019/06/07 · arxiv updated 2019/06/10

Abstract

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose a larger-scale dataset with larger domain discrepancy: UCF-HMDB_full. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets. The code and data are released at http://github.com/cmhungsteve/TA3N.

Related

• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
• Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
• Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
• GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap
• Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network