You have already added 0 works in your ORCID record related to the merged Research product.
You have already added 0 works in your ORCID record related to the merged Research product.
Learning Context Graph for Person Search
Learning Context Graph for Person Search
Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.
Comment: To appear in CVPR 2019
- Inception Institute of Artificial Intelligence United Arab Emirates
- Shanghai Jiao Tong University China (People's Republic of)
Microsoft Academic Graph classification: Convolutional neural network Computer science Artificial intelligence business.industry business Graph (abstract data type) Visual reasoning Categorization Embedding Feature learning
Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, Computer Science - Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, Computer Science - Computer Vision and Pattern Recognition
Microsoft Academic Graph classification: Convolutional neural network Computer science Artificial intelligence business.industry business Graph (abstract data type) Visual reasoning Categorization Embedding Feature learning
5716
[1] Ejaz Ahmed, Michael J. Jones, and Tim K. Marks. An improved deep learning architecture for person reidentification. In CVPR, pages 3908-3916, 2015.
[2] Shayan Modiri Assari, Haroon Idrees, and Mubarak Shah. Human re-identification in crowd videos using personal, social and environmental constraints. In ECCV, pages 119- 136, 2016. [OpenAIRE]
[3] A. Bedagkar-Gala and Shishir K. Shah. Part-based spatiotemporal model for multi-person re-identification. Pattern Recognition Letters, 33(14):1908 - 1915, 2012.
[4] Min Cao, Chen Chen, Xiyuan Hu, and Silong Peng. From groups to co-traveler sets: Pair matching based person reidentification framework. In ICCV Workshops, pages 2573- 2582, 2017.
[5] Dapeng Chen, Dan Xu, Hongsheng Li, Nicu Sebe, and Xiaogang Wang. Group consistent similarity learning via deep CRF for person re-identification. In CVPR, pages 8649- 8658, 2018.
[6] Dapeng Chen, Zejian Yuan, Badong Chen, and Nanning Zheng. Similarity learning with spatial constraints for person re-identification. In CVPR, pages 1268-1277, 2016.
[7] Di Chen, Shanshan Zhang, Wanli Ouyang, Jian Yang, and Ying Tai. Person search via a mask-guided two-stream CNN model. In ECCV, pages 764-781, 2018.
[8] Weihua Chen, Xiaotang Chen, Jianguo Zhang, and Kaiqi Huang. Beyond triplet loss: A deep quadruplet network for person re-identification. In CVPR, pages 1320-1329, 2017.
[9] De Cheng, Yihong Gong, Zhihui Li, Dingwen Zhang, Weiwei Shi, and Xingjun Zhang. Cross-scenario transfer metric learning for person re-identification. Pattern Recognition Letters, 2018.
[10] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Fei-Fei Li. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.
citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).83 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Substantial influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Substantial citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).83 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Substantial influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Substantial
Citations provided by BIP!Popularity provided by BIP!
- Inception Institute of Artificial Intelligence United Arab Emirates
- Shanghai Jiao Tong University China (People's Republic of)
Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.
Comment: To appear in CVPR 2019