Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals
By Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang. IEEE International Conference on Computer Vision, 2017
300 citations recorded by the source corpus.
Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation. It gains increasing attention because of the recent advances of person re-identification techniques. However, unlike person re-identification, the visual differences between pairs of vehicle images are usually subtle and even challenging for humans to distinguish. Incorporating additional spatio-temporal information is vital for solving the challenging re-identification task. Existing vehicle re-identification methods ignored or used oversimplified models for the spatio-temporal relations between vehicle images. In this paper, we propose a two-stage framework that incorporates complex spatio-temporal information for effectively regularizing the re-identification results. Given a pair of vehicle images with their spatiotemporal information, a candidate visual-spatio-temporal path is first generated by a chain MRF model with a deeply learned potential function, where each visual-spatiotemporal state corresponds to an actual vehicle image with its spatio-temporal information. A Siamese-CNN+Path- LSTM model takes the candidate path as well as the pairwise queries to generate their similarity score. Extensive experiments and analysis show the effectiveness of our proposed method and individual components.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/86eab1845deb3614233360b6bc33ce1ff074458e
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
- Jun Liu
- Ling-yu Duan
- Jun-Cheng Chen
- Ramalingam Chellappa
- G. Wang
- Weixin Liang
- Wen-mei W. Hwu
- Yan Bai
Citations in the corpus
- Continual egocentric object recognition (2019, background): “The most prominent applications in this field are related to the iden-tification of humans [35], with some works focusing on vehicle re-identification [29].”
- VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild (2019, background): “[18] proposed a two-stage framework that incorporates complex spatial-temporal information for effectively regularizing the ReID results.”
- The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification (2020, methodology): “[25, 26, 34, 38, 14, 29, 15] propose methods for improving the matching performance by also making use of spatio-temporal and multi-modal information, such as visual features, license plates, inter-camera vehicle trajectories, camera locations, and time stamps.”
- DeepStore: In-Storage Acceleration for Intelligent Queries (2019, background): “We believe these identified intelligent query applications show the generality of emerging intelligent query systems [23, 30, 43, 46, 51, 57, 69, 83, 84, 102].”