Re-id: Hunting Attributes in the Wild

By Ryan Layne, Timothy M. Hospedales, Shaogang Gong. 2014

71 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ecology, Geography, Planning and Development

How researchers see this paper

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

In Computer Vision and Pattern Recognition

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

In Ecology

1. Tao A. Xiang
2. Shaogang Gong
3. Xiatian Zhu
4. Jingya Wang
5. Qi Tian

In Geography, Planning and Development

1. Tao A. Xiang
2. Shaogang Gong
3. Xiatian Zhu
4. Jingya Wang

Citations in the corpus

• Transductive Multi-View Zero-Shot Learning (2015, methodology): “Zero-shot learning Multi-class single label zero-shot learning has now been widely studied using attribute-based intermediate semantic layers [3, 6, 10, 11, 19, 25] or data-driven [8, 9, 21, 30] representations.”
• Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “set of machine-detectable attributes. These attributes can be a set of nameable image characteristics and semantic concepts [84, 130, 158, 88], or latent topics discovered by the system from the data [199, 131, 89]. In both cases, detecting these attributes can be seen as the common tasks between th”
• Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, background): “In person re-identification, attributes show promising performance in preserving consistent representations of the same person and identifying differences among different persons [31], [43], [44], [45].”
• Deep Attributes Driven Multi-Camera Person Re-identification (2016, background): “The experimental results show that deep attributes perform impressively, e.g. , they significantly outperform many recent works combining both attributes and local features [29,30,31,32].”
• Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, background): “For person re-identification, attributes are powerful in preserving consistent representations of the same person and capturing differences among different people [29, 26, 27, 28].”
• Improving Person Re-identification by Attribute and Identity Learning (2017, methodology): “In [17, 16, 15], low-level descriptors and SVM is used to train attribute detectors, and the attributes are integrated in several metric learning methods.”
• 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].”
• Unsupervised Cross-Dataset Transfer Learning for Person Re-identification (2016, methodology): “To address these challenges, most existing research efforts on Re-ID [25, 15, 16, 4, 20, 37, 39, 36, 23, 31, 2] are based on supervised learning.”