2017/12/06 by Xuelin Qian, Qian, Xuelin, Yanwei Fu +14 · 5 citations
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Human Pose and Action Recognition #Machine Learning (stat.ML) #Multimedia (cs.MM) #Video Surveillance and Tracking Methods #cs.AI #cs.CV #cs.MM #stat.ML
paper · pdf · doi:10.48550/arxiv.1712.02225
10 pages, 5 figures
openalex publication_date 2017/12/06 · arxiv created 2018/04/25 · arxiv updated 2018/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on the pose. The model is based on a generative adversarial network (GAN) designed specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). With the synthesized images, we can learn a new type of deep re-id feature free of the influence of pose variations. We show that this feature is strong on its own and complementary to features learned with the original images. Importantly, under the transfer learning setting, we show that our model generalizes well to any new re-id dataset without the need for collecting any training data for model fine-tuning. The model thus has the potential to make re-id model truly scalable.