ABSTRACT
Vehicle re-identification aims to identify the same vehicle across different surveillance cameras and plays an important role in public security. Existing approaches mainly focus on exploring informative regions or learning an appropriate distance metric. However, they not only neglect the inherent structured relationship between discriminative regions within an image, but also ignore the extrinsic structured relationship among images. The inherent and extrinsic structured relationships are crucial to learning effective vehicle representation. In this paper, we propose a Structured Graph ATtention network (SGAT) to fully exploit these relationships and allow the message propagation to update the features of graph nodes. SGAT creates two graphs for one probe image. One is an inherent structured graph based on the geometric relationship between the landmarks that can use features of their neighbors to enhance themselves. The other is an extrinsic structured graph guided by the attribute similarity to update image representations. Experimental results on two public vehicle re-identification datasets including VeRi-776 and VehicleID have shown that our proposed method achieves significant improvements over the state-of-the-art methods.
Supplemental Material
- Yan Bai, Yihang Lou, Feng Gao, Shiqi Wang, Yuwei Wu, and Ling-Yu Duan. 2018. Group-Sensitive Triplet Embedding for Vehicle Re-Identification. IEEE Transactions on Multimedia, Vol. 20, 9 (2018), 2385--2399.Google ScholarDigital Library
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral Networks and Locally Connected Networks on Graphs. International Conference on Learning Representations (2014).Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In Advances in Neural Information Processing Systems. 3844--3852.Google Scholar
- Yan Em, Feng Gag, Yihang Lou, Shiqi Wang, Tiejun Huang, and Ling-Yu Duan. 2017. Incorporating Intra-Class Variance to Fine-Grained Visual Recognition. In International Conference on Multimedia and Expo. IEEE, 1452--1457.Google ScholarCross Ref
- Junyu Gao, Tianzhu Zhang, and Changsheng Xu. 2019. Graph Convolutional Tracking. In Computer Vision and Pattern Recognition. IEEE.Google Scholar
- Haiyun Guo, Chaoyang Zhao, Zhiwei Liu, Jinqiao Wang, and Hanqing Lu. 2018. Learning Coarse-to-Fine Structured Feature Embedding for Vehicle Re-Identification. In AAAI Conference on Artificial Intelligence.Google Scholar
- Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep Convolutional Networks on Graph-Structured Data. arXiv preprint arXiv:1506.05163 (2015).Google Scholar
- Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In Defense of the Triplet Loss for Person Re-Identification. arXiv preprint arXiv:1703.07737 (2017).Google Scholar
- Yukun Huang, Zheng-Jun Zha, Xueyang Fu, Richang Hong, and Liang Li. 2020. Real-World Person Re-Identification via Degradation Invariance Learning. In Computer Vision and Pattern Recognition. IEEE.Google Scholar
- Aytacc Kanaci, Xiatian Zhu, and Shaogang Gong. 2017. Vehicle Re-Identification by Fine-Grained Cross-Level Deep Learning. In The British Machine Vision Conference Workshop, Vol. 2. 772--788.Google Scholar
- Pirazh Khorramshahi, Amit Kumar, Neehar Peri, Sai Saketh Rambhatla, Jun-Cheng Chen, and Rama Chellappa. 2019. A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification. In International Conference on Computer Vision. IEEE.Google ScholarCross Ref
- Thomas N Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (2017).Google Scholar
- John Boaz Lee, Ryan Rossi, and Xiangnan Kong. 2018. Graph Classification Using Structural Attention. In International Conference on Knowledge Discovery and Data Mining. ACM, 1666--1674.Google Scholar
- Yuqi Li, Yanghao Li, Hongfei Yan, and Jiaying Liu. 2017. Deep Joint Discriminative Learning for Vehicle Re-Identification and Retrieval. In International Conference on Image Processing. IEEE, 395--399.Google Scholar
- Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li. 2015. Person Re-Identification by Local Maximal Occurrence Representation and Metric Learning. In Computer Vision and Pattern Recognition. IEEE, 2197--2206.Google Scholar
- Hongye Liu, Yonghong Tian, Yaowei Yang, Lu Pang, and Tiejun Huang. 2016c. Deep Relative Distance Learning: Tell the Difference between Similar Vehicles. In Computer Vision and Pattern Recognition. IEEE, 2167--2175.Google Scholar
- Jiawei Liu, Zheng-Jun Zha, Di Chen, Richang Hong, and Meng Wang. 2019 a. Adaptive Transfer Network for Cross-Domain Person Re-Identification. In Computer Vision and Pattern Recognition. IEEE, 7202--7211.Google Scholar
- Jiawei Liu, Zheng-Jun Zha, Xuejin Chen, Zilei Wang, and Yongdong Zhang. 2019 b. Dense 3d-Convolutional Neural Network for Person Re-identification in Videos. ACM Transactions on Multimedia Computing, Communications, and Applications, Vol. 15, 1s (2019), 8.Google ScholarDigital Library
- Jiawei Liu, Zheng-Jun Zha, QI Tian, Dong Liu, Ting Yao, Qiang Ling, and Tao Mei. 2016 d. Multi-Scale Triplet CNN for Person Re-Identification. In ACM international conference on Multimedia. ACM, 192--196.Google Scholar
- Jiawei Liu, Zheng-Jun Zha, Hongtao Xie, Zhiwei Xiong, and Yongdong Zhang. 2018a. CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification. In ACM International Conference on Multimedia. ACM, 737--745.Google ScholarDigital Library
- Xinchen Liu, Wu Liu, Huadong Ma, and Huiyuan Fu. 2016a. Large-scale Vehicle Re-Identification in Urban Surveillance Videos. In International Conference on Multimedia and Expo. IEEE, 1--6.Google Scholar
- Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. 2016b. A Deep Learning-Based Approach to Progressive Vehicle Re-Identification for Urban Surveillance. In European Conference on Computer Vision. Springer, 869--884.Google ScholarCross Ref
- Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. 2017. Provid: Progressive and Multimodal Vehicle Re-Identification for Large-Scale Urban Surveillance. IEEE Transactions on Multimedia, Vol. 20, 3 (2017), 645--658.Google ScholarDigital Library
- Xiaobin Liu, Shiliang Zhang, Qingming Huang, and Wen Gao. 2018b. RAM: A Region-Aware Deep Model for Vehicle Re-Identification. In International Conference on Multimedia and Expo. IEEE, 1--6.Google Scholar
- Yihang Lou, Yan Bai, Jun Liu, Shiqi Wang, and Ling-Yu Duan. 2019. Embedding Adversarial Learning for Vehicle Re-Identification. IEEE Transactions on Image Processing (2019).Google Scholar
- Kenneth Marino, Ruslan Salakhutdinov, and Abhinav Gupta. 2017. The More You Know: Using Knowledge Graphs for Image Classification. (2017), 2673--2681.Google Scholar
- Dechao Meng, Liang Li, Xuejing Liu, Yadong Li, Shijie Yang, Zheng-Jun Zha, Xingyu Gao, Shuhui Wang, and Qingming Huang. 2020 a. Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification. In Computer Vision and Pattern Recognition. IEEE, 7103--7112.Google Scholar
- Dechao Meng, Liang Li, Shuhui Wang, Zheng-Jun Zha, Xingyu Gao, and Qingming Huang. 2020 b. Fine-Grained Feature Alignment with Part Perspective Transformation for Vehicle ReID. In ACM International Conference on Multimedia. ACM.Google Scholar
- Will Norcliffe-Brown, Stathis Vafeias, and Sarah Parisot. 2018. Learning Conditioned Graph Structures for Interpretable Visual Question Answering. In Advances in Neural Information Processing Systems. 8334--8343.Google Scholar
- Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in Pytorch. (2017).Google Scholar
- Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, and Xiaogang Wang. 2017. Learning Deep Neural Networks for Vehicle Re-Id with Visual-Spatio-Temporal Path Proposals. In International Conference on Computer Vision. IEEE, 1900--1909.Google Scholar
- Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. International Conference on Learning Representations (2015).Google Scholar
- Yong Tang, Congzhe Zhang, Renshu Gu, Peng Li, and Bin Yang. 2017. Vehicle Detection and Recognition for Intelligent Traffic Surveillance System. Multimedia Tools and Applications, Vol. 76, 4 (2017), 5817--5832.Google ScholarDigital Library
- Shangzhi Teng, Xiaobin Liu, Shiliang Zhang, and Qingming Huang. 2018. SCAN: Spatial and Channel Attention Network for Vehicle Re-Identification. In Pacific Rim Conference on Multimedia. Springer, 350--361.Google Scholar
- Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph Attention Networks. International Conference on Learning Representations (2018).Google Scholar
- Xiaolong Wang and Abhinav Gupta. 2018. Videos as Space-Time Region Graphs. In European Conference on Computer Vision. Springer, 399--417.Google ScholarCross Ref
- Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. 2019. Dynamic graph cnn for learning on point clouds. ACM Transactions On Graphics, Vol. 38, 5 (2019), 1--12.Google ScholarDigital Library
- Zheng Wang, Ruimin Hu, Chao Liang, Yi Yu, Junjun Jiang, Mang Ye, Jun Chen, and Qingming Leng. 2015. Zero-Shot Person Re-Identification via Cross-View Consistency. IEEE Transactions on Multimedia, Vol. 18, 2 (2015), 260--272.Google ScholarDigital Library
- Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, and Xiaogang Wang. 2017. Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-Identification. In International Conference on Computer Vision. IEEE, 379--387.Google Scholar
- Xiu-Shen Wei, Chen-Lin Zhang, Lingqiao Liu, Chunhua Shen, and Jianxin Wu. 2018. Coarse-to-Fine: A RNN-based Hierarchical Attention Model for Vehicle Re-Identification. Asian Conference on Computer Vision (2018).Google Scholar
- Lin Wu, Yang Wang, Junbin Gao, and Xue Li. 2018. Where-and-When to Look: Deep Siamese Attention Networks for Video-Based Person Re-Identification. IEEE Transactions on Multimedia, Vol. 21, 6 (2018), 1412--1424.Google ScholarDigital Library
- Bin Xiao, Haiping Wu, and Yichen Wei. 2018. Simple Baselines for Human Pose Estimation and Tracking. In European Conference on Computer Vision. Springer, 466--481.Google Scholar
- Ke Yan, Yonghong Tian, Yaowei Wang, Wei Zeng, and Tiejun Huang. 2017. Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-Similar Vehicles. In International Conference on Computer Vision. IEEE, 562--570.Google Scholar
- Zheng-Jun Zha, Jiawei Liu, Di Chen, and Feng Wu. 2020. Adversarial Attribute-Text Embedding for Person Search With Natural Language Query. IEEE Transactions on Multimedia, Vol. 22, 7 (2020), 1836--1846.Google ScholarCross Ref
- Junping Zhang, Fei-Yue Wang, Kunfeng Wang, Wei-Hua Lin, Xin Xu, and Cheng Chen. 2011. Data-Driven Intelligent Transportation Systems: A Survey. IEEE Transactions on Intelligent Transportation Systems, Vol. 12, 4 (2011), 1624--1639.Google ScholarDigital Library
- Li Zhang, Tao Xiang, and Shaogang Gong. 2016. Learning a Discriminative Null Space for Person Re-Identification. In Computer Vision and Pattern Recognition. IEEE, 1239--1248.Google Scholar
- Muhan Zhang, Zhicheng Cui, Marion Neumann, and Yixin Chen. 2018. An End-to-End Deep Learning Architecture for Graph Classification. In AAAI Conference on Artificial Intelligence.Google Scholar
- Yiheng Zhang, Dong Liu, and Zheng-Jun Zha. 2017. Improving Triplet-Wise Training of Convolutional Neural Network for Vehicle Re-identification. In International Conference on Multimedia and Expo. IEEE, 1386--1391.Google Scholar
- Yu Zheng, Licia Capra, Ouri Wolfson, and Hai Yang. 2014. Urban Computing: Concepts, Methodologies, and Applications. ACM Transactions on Intelligent Systems and Technology, Vol. 5, 3 (2014), 38.Google ScholarDigital Library
- Yi Zhou and Ling Shao. 2017. Cross-View GAN Based Vehicle Generation for Re-Identification.. In The British Machine Vision Conference, Vol. 1. 1--12.Google ScholarCross Ref
- Yi Zhou and Ling Shao. 2018a. Vehicle Re-Identification by Adversarial Bi-Directional LSTM Network. In Winter Conference on Applications of Computer Vision. IEEE, 653--662.Google ScholarCross Ref
- Yi Zhou and Ling Shao. 2018b. Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification. In Computer Vision and Pattern Recognition. IEEE.Google Scholar
- Jianqing Zhu, Huanqiang Zeng, Jingchang Huang, Shengcai Liao, Zhen Lei, Canhui Cai, and Lixin Zheng. 2019. Vehicle Re-Identification Using Quadruple Directional Deep Learning Features. IEEE Transactions on Intelligent Transportation Systems (2019).Google Scholar
Index Terms
- A Structured Graph Attention Network for Vehicle Re-Identification
Recommendations
Global reference attention network for vehicle re-identification
AbstractVehicle re-identification (Re-ID) aims to find the image of the same vehicle in different cameras. One of the reasons that this task remains challenging is that different vehicles of the same type and color look very similar in appearance. In ...
HSS-GCN: A Hierarchical Spatial Structural Graph Convolutional Network for Vehicle Re-identification
Pattern Recognition. ICPR International Workshops and ChallengesAbstractVehicle re-identification (Re-ID) is the task aiming to identify the same vehicle from images captured by different cameras. Recent years have seen various appearance-based approaches focusing only on global features or exploring local features to ...
A Dual Self-Attention mechanism for vehicle re-Identification
Highlights- A novel multi-attention network simulating the visual attention of humans is designed to realize highly efficient alignment and feature embedding globally ...
AbstractVehicle re-identification has attracted tremendous attention from computer vision communities for its extensive applications in intelligent transportation and public security, while the high inter-class similarity and the large intra-...
Comments