A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking

Abstract

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose information of the person to learn a discriminative embedding. In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation. To increase retrieval performance, re-ranking techniques based on computed distances have recently gained much attention. We propose a new unsupervised and automatic re-ranking framework that achieves state-of-the-art re-ranking performance. We show that in contrast to the current state-of-the-art re-ranking methods our approach does not require to compute new rank lists for each image p

Stats

• citations356
• S2 citations—
• github stars112
• HF likes0
• heat score23.25
• arxiv keysarfraz2017a

Related papers

• Part-aligned Bilinear Representations For Person Re-identification (2018)19.30
• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Neighbor-based Feature And Index Enhancement For Person Re-identification (2025)0.00
• Pose Invariant Embedding For Deep Person Re-identification (2017)19.34
• Maskreid: A Mask Based Deep Ranking Neural Network For Person Re-identification (2018)0.00
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Pgganet: Pose Guided Graph Attention Network For Person Re-identification (2021)0.00
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00