12 citations · 12 across the 2 of their papers we have counts for
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2019
SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
Yan Huang, Qiang Wu, JingSong Xu +1
Cross-domain person re-identification (re-ID) is challenging due to the bias between training and testing domains. We observe that if backgrounds in the training and testing datase…
cs.CV2019
Learning Compact Target-Oriented Feature Representations for Visual Tracking
Chenglong Li, Yan Huang, Liang Wang +2
Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundan…
cs.CV2019★ 12 cited
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
Kai Niu, Yan Huang, Wanli Ouyang +1
Description-based person re-identification (Re-id) is an important task in video surveillance that requires discriminative cross-modal representations to distinguish different peop…