paper-with-me

Papers

A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification

2019-05-09 · ICCV 2019 10 · Pirazh Khorramshahi, Amit Kumar, Neehar Peri, Sai Saketh Rambhatla, Jun-Cheng Chen, Rama Chellappa

In recent years, attention models have been extensively used for person and vehicle re-identification. Most re-identification methods are designed to focus attention on key-point locations. However, depending on the orientation, the contribution of each key-point varies. In this paper, we present a novel dual-path adaptive attention model for vehicle re-identification (AAVER). The global appearance path captures macroscopic vehicle features while the orientation conditioned part appearance path learns to capture localized discriminative features by focusing attention on the most informative key-points. Through extensive experimentation, we show that the proposed AAVER method is able to accurately re-identify vehicles in unconstrained scenarios, yielding state of the art results on the challenging dataset VeRi-776. As a byproduct, the proposed system is also able to accurately predict vehicle key-points and shows an improvement of more than 7% over state of the art. The code for key-point estimation model is available at https://github.com/Pirazh/Vehicle_Key_Point_Orientation_Estimation.

📄 PDF Abstract BibTeX arXiv:1905.03397

Code (1)

Pirazh/Vehicle_Key_Point_Orientation_Estimation 공식 구현 pytorch

Tasks

Vehicle Key-Point and Orientation EstimationVehicle Re-Identification

Similar Papers 제목 키워드 기반

Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals

2017-08-13 · ICCV 2017 10 · Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi 외

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 t…

Person Re-IdentificationVehicle Re-Identification

Multimodality Adaptive Transformer and Mutual Learning for Unsupervised Domain Adaptation Vehicle Re-Identification

2024-09-17 · IEEE Transactions on Intelligent Transportation Systems 2024 9 · Xin Zhang, Yunan Ling, Kaige Li, Weimin Shi 외

Unsupervised Domain Adaptation Vehicle Re-Identification (UDA vehicle re-ID) aims to enable the model trained in the source domain dataset to adapt to the target domain data and obtain accurate re-identification results,…

AttributeDomain AdaptationPseudo LabelUnsupervised Domain Adaptation+1

Image-based Vehicle Re-identification Model with Adaptive Attention Modules and Metadata Re-ranking

2020-07-03 · Quang Truong, Hy Dang, Zhankai Ye, Minh Nguyen 외

Vehicle Re-identification is a challenging task due to intra-class variability and inter-class similarity across non-overlapping cameras. To tackle these problems, recently proposed methods require additional annotation …

Re-RankingVehicle Re-Identification

A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification

2023-06-25 · Xiaoyan Guo, Jie Yang, Xinyu Jia, Chuanyan Zang 외

Vehicle re-identification (Re-ID) involves identifying the same vehicle captured by other cameras, given a vehicle image. It plays a crucial role in the development of safe cities and smart cities. With the rapid growth …

Single Particle AnalysisTripletVehicle Re-Identification

ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-Identification

2023-02-11 · Jing Yang, Jianwu Fang, Hongke Xu

Vehicle re-identification is a cross-view search task by matching the same target vehicle from different perspectives. It serves an important role in road-vehicle collaboration and intelligent road control. With the larg…

Self-Supervised LearningUnsupervised Vehicle Re-IdentificationVehicle Re-Identification