Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification

By Chi Su, Fan Yang, Shiliang Zhang, Qi Tian, Larry S. Davis, Wen Gao. 2015

190 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

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. Zhedong Zheng
4. Qi Tian
5. Shiliang Zhang
6. Wen Gao
7. Shengjin Wang
8. Shaogang Gong

In Computer Vision and Pattern Recognition

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

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “…images include object categorization [86], image segmentation [89,90], identifying brain imaging predictors [91], saliency detection [92], action recognition [93], scene classification [94], multi-attribute prediction [95], multi-camera person re-identification [96], and immediacy prediction [97].”
• Cross-Stitch Networks for Multi-task Learning (2016, background): “However, most of such work, with publicly available code, formulates multi-task learning in an optimization framework that requires all data points in memory [6, 14, 23, 34, 49, 60, 61].”
• A Survey on Multi-Task Learning (2017, methodology): “In [177], similar to [100], a decomposition model with one component modeling low-rank”
• Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification (2017, methodology): “Most of existing methods in person ReID focus on either feature extraction [44, 28, 23, 8, 40], or similarity measurement [17, 27, 22, 39].”
• Improving Person Re-identification by Attribute and Identity Learning (2017, methodology): “[27] learn a discriminative model by multi-task learning, which exploits features and attributes shared by different cameras.”
• Unsupervised Person Re-Identification via Multi-Label Classification (2020, background): “Recent years have witnessed the great success of person re-identification (ReID), which learns discriminative features from labeled person images with deep Convolutional Neural Network (CNN) [43, 14, 9, 27, 16, 26, 28, 29].”
• Part-Aligned Bilinear Representations for Person Re-identification (2018, background): “Recently, attributes [51, 52, 77], transfer learning [43, 49], re-ranking [81, 15], partial person matching [83], and human-in-the-loop learning [38, 61], have also been studied.”
• MARS: A Video Benchmark for Large-Scale Person Re-Identification (2016, methodology): “Among them, the first mode is mostly studied in literature, and previous methods in imagebased re-id [5,24,35] are developed in adaptation to the poor amount of training”
• Deeply-Learned Part-Aligned Representations for Person Re-identification (2017, background): “Person attributes or salient patterns, such as female/male, wearing hat or not, have also been exploited to distinguish persons [40, 41, 61].”
• Gated Siamese Convolutional Neural Network Architecture for Human Re-identification (2016, background): “Existing research on human re-identification mainly concentrates on two aspects: (1) Developing a new feature representation [5, 19, 24, 29, 44, 50, 51, 55] and (2) Learning a distance metric [20, 23, 24, 25, 32, 34, 41, 49].”
• Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification (2018, methodology): “Attribute for Re-ID Visual attributes have been exploited as a mid-level feature representation for cross-view re-id [24, 22, 23, 43, 42, 36].”
• Deep Attributes Driven Multi-Camera Person Re-identification (2016, methodology): “, they significantly outperform many recent works combining both attributes and local features [29,30,31,32].”
• Scalable Person Re-identification on Supervised Smoothed Manifold (2017, unknown): “37 MTL-LORAE [46] ICCV2015 42.”
• A Siamese Long Short-Term Memory Architecture for Human Re-identification (2016, unknown): “MT-LORAE [49] 42.”