mlsanityData to 7 Oct 2026

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

arXiv 1905.03397 ↗First posted 9 May 2019cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 10; 2023: 7; 2024: 4.

34 papers.

Sort:

  1. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  2. 2021GiT: Graph Interactive Transformer for Vehicle Re-identificationcited by 49
  3. 2021Heterogeneous Relational Complement for Vehicle Re-identificationcited by 25
  4. 2024Transformer for Object Re-Identification: A Surveycited by 21
  5. 2022Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmarkcited by 17
  6. 2023Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identificationcited by 14
  7. 2024A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challengescited by 9
  8. 2021Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systemscited by 8
  9. 2021Learning Canonical 3D Object Representation for Fine-Grained Recognitioncited by 7
  10. 2021A Synthesis-Based Approach for Thermal-to-Visible Face Verificationcited by 7
  11. 2023CAROM Air -- Vehicle Localization and Traffic Scene Reconstruction from Aerial Videoscited by 7
  12. 2021Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Reviewcited by 6
22 more
  1. 2021ES-Net: Erasing Salient Parts to Learn More in Re-Identificationcited by 6
  2. 2022HSGNet: Object Re-identification with Hierarchical Similarity Graph Networkcited by 6
  3. 2021An Empirical Study of Vehicle Re-Identification on the AI City Challengecited by 5
  4. 2022A Brief Survey on Person Recognition at a Distancecited by 4
  5. 2024Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Surveycited by 4
  6. 2022Face Shape-Guided Deep Feature Alignment for Face Recognition Robust to Face Misalignmentcited by 2
  7. 2023Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metriccited by 2
  8. 2021Instance and Pair-Aware Dynamic Networks for Re-Identificationcited by 1
  9. 2021Multi-Attention-Based Soft Partition Network for Vehicle Re-Identificationcited by 1
  10. 2022Self-aligned Spatial Feature Extraction Network for UAV Vehicle Re-identificationcited by 1
  11. 2022Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Trackingcited by 1
  12. 2022Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identificationcited by 1
  13. 2022Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identificationcited by 1
  14. 2023Spatial-temporal Vehicle Re-identificationcited by 1
  15. 2023VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identificationcited by 1
  16. 2021Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identificationcited by 0
  17. 2021Center Prediction Loss for Re-identificationcited by 0
  18. 2022Discriminative-Region Attention and Orthogonal-View Generation Model for Vehicle Re-Identificationcited by 0
  19. 2022Scalable Vehicle Re-Identification via Self-Supervisioncited by 0
  20. 2023Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)cited by 0
  21. 2023Beyond Sharing Weights in Decoupling Feature Learning Network for UAV RGB-Infrared Vehicle Re-Identificationcited by 0
  22. 2024Object Re-identification via Spatial-temporal Fusion Networks and Causal Identity Matchingcited by 0