Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
Pattern Recognition, Volume abs/1706.03160, 2018.
Abstract Person re-identification (re-id) aims to match pedestrians observed by disjoint camera views. It attracts increasing attention in computer vision due to its importance to surveillance systems. To combat the major challenge of cross-view visual variations, deep embedding approaches are proposed by learning a compact feature spac...More
Full Text (Upload PDF)
PPT (Upload PPT)