Person Re-identification in the Wild

Abstract

We present a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification. We make three distinct contributions. First, a new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, using videos acquired through six synchronized cameras. It contains 932 identities and 11,816 frames in which pedestrians are annotated with their bounding box positions and identities. Extensive benchmarking results are presented on this dataset. Second, we show that pedestrian detection aids re-identification through two simple yet effective improvements: a discriminatively trained ID-discriminative Embedding (IDE) in the person subspace using convolutional neural network (CNN) features and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Third, we derive insights in evaluating detector performance for the particular scenario of accurate person re-identification.

accepted as spotlight to CVPR 2017

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Person Re-identification: Past, Present and Future
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• Re-ranking Person Re-identification with k-reciprocal Encoding
• Open-set Person Re-identification
• Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues

Cited by in corpus (18)

• Person Re-identification: Past, Present and Future
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• Pose Invariant Embedding for Deep Person Re-identification
• Re-ranking Person Re-identification with k-reciprocal Encoding
• Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
• Joint Person Re-identification and Camera Network Topology Inference in Multiple Cameras
• Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
• Identity-Aware Textual-Visual Matching with Latent Co-attention
• Pose-Normalized Image Generation for Person Re-identification
• Neural Person Search Machines
• Video-based Person Re-identification with Accumulative Motion Context
• Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
• Deep Reinforcement Learning Attention Selection for Person Re-Identification
• IAN: The Individual Aggregation Network for Person Search
• Unified Framework for Automated Person Re-identification and Camera Network Topology Inference in Camera Networks
• Deep Person Re-Identification with Improved Embedding and Efficient Training