BriefGPT.xyz
May, 2019
视频域自适应的时间关注对齐
Temporal Attentive Alignment for Video Domain Adaptation
HTML
PDF
Chen, Min-Hung, Kira, Zsolt, AlRegib...
TL;DR
本研究提出了一个更大规模的视频领域自适应数据集UCF-HMDB_full,并探究了不同的 Integration 方法以及通过指定领域距离来显式关注时间动态的方法TA3N来实现更有效的域适应。
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 d
→