Pose-Aware Person Recognition
This work addresses pose challenges in person recognition for applications like surveillance and photo organization, representing an incremental advance over existing multi-region methods.
The paper tackles extreme pose and viewpoint variations in full-body person recognition by training multiple models on specific poses and combining them with pose-aware weights, achieving significant improvements on new benchmarks including PIPA's photo album setting.
Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme variation in pose and view point. In this work, (i) we present an approach that tackles pose variations utilizing multiple models that are trained on specific poses, and combined using pose-aware weights during testing. (ii) For learning a person representation, we propose a network that jointly optimizes a single loss over multiple body regions. (iii) Finally, we introduce new benchmarks to evaluate person recognition in diverse scenarios and show significant improvements over previously proposed approaches on all the benchmarks including the photo album setting of PIPA.