Partial Person Re-Identification

By Weishi Zheng, Xiang Li, Tao A. Xiang, Shengcai Liao, J. Lai, Shaogang Gong. IEEE International Conference on Computer Vision, 2015

301 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3d30eaf1c5e4844f0319ff03993cf1d1af735ee7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Yi Yang
2. Liang Zheng
3. Shaogang Gong
4. Qi Tian
5. Wanli Ouyang
6. Tao A. Xiang
7. Xiatian Zhu
8. Mang Ye

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Xiaogang Wang
3. Luc Van Gool
4. Liang Zheng
5. Dacheng Tao
6. Ming-Hsuan Yang
7. Qi Tian
8. Ling Shao

Citations in the corpus

• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, unknown): “[35], [36], [37], [38], [39], [40], [41], [42], [43] dominate cur-”
• Harmonious Attention Network for Person Re-identification (2018, methodology): “One common strategy is local patch calibration and saliency weighting in pairwise image matching [43, 25, 46, 36].”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “This addresses the Re-ID problem with heavy occlusions, i.e ., only part of the human body is visible [223].”
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “Like occluded person ReID, partial person ReID [45] aims to match partial probe images to gallery holistic images.”
• Person Re-identification in the Wild (2016, background): “Finally, effective partial re-ID algorithms [49] can be important for end-to-end systems on the PRW dataset (Fig.”
• Pose-Guided Feature Alignment for Occluded Person Re-Identification (2019, methodology): “Partial-REID [45] is a specially designed partial person dataset that includes 600 images from 60 people, with five full-body images and five partial images per person.”
• Recurrent Attention Models for Depth-Based Person Identification (2016, background): “There have been many attempts to solve this problem by improving the feature representations [24, 68, 22, 78, 79, 37, 80] and by exploring new similarity metrics [40, 49, 60].”
• Person Re-identification: Past, Present and Future (2016, background): “In [29] can be used to eliminate false positives which do not contain or provide good localization of a human body.”
• End-to-End Deep Learning for Person Search (2016, background): “[42] proposed a local-global matching framework for paritially occluded pedestrian images.”
• Part-Aligned Bilinear Representations for Person Re-identification (2018, background): “Recently, attributes [33–35], transfer learning [36, 37], re-ranking [38, 39], partial person matching [40], and human-in-the-loop learning [41,42], have also been studied.”
• Attention-Aware Compositional Network for Person Re-identification (2018, background): “of features, namely global features extracted from the whole image [11, 44] and region features generated from local patches [51, 57, 22].”
• Distilled Person Re-Identification: Towards a More Scalable System (2019, background): “Person Reidentification has witnessed a fast growing development in recent years, from feature design [19, 15, 32, 31, 35, 69, 58] to distance metric learning [54, 19, 43, 25, 67, 36, 41, 30, 58, 33, 38, 31, 9, 68, 60, 63, 69, 29, 52, 6] and end-to-end deep learning [28, 1, 55, 57, 49, 22, 64, 65, 7”
• Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification (2019, methodology): “Partial-REID [36] and Partial-iLIDS [35] are two commonly-used datasets for partial re-ID.”
• Joint Detection and Identification Feature Learning for Person Search (2016, background): “Several recent works addressed on solving person re-id on abnormal images, such as low-resolution images [20], or partially occluded images [46].”
• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “(1) The hand-crafted splitting based methods divide the image or feature map into small patches [10, 57, 12] or rigid stripes [38, 4] and then extract part features from the local patches or stripes.”
• Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach (2018, methodology): “[32] proposed a local patchlevel matching model called Ambiguity-sensitive Matching Classifier (AMC) based on dictionary learning with explicit patch ambiguity modeling, and introduced a global partbased matching model called Sliding Window Matching (SWM) that can provide complementary spatial layou”