mlsanityData to 7 Oct 2026

Vehicle Re-identification with Viewpoint-aware Metric Learning

arXiv 1910.04104 ↗First posted 9 Oct 2019cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the behavior in human's recognition process, we propose a novel viewpoint-aware metric learning approach. It learns two metrics for similar viewpoints and different viewpoints in two feature spaces, respectively, giving rise to viewpoint-aware network (VANet). During training, two types of constraints are applied jointly. During inference, viewpoint is firstly estimated and the corresponding metric is used. Experimental results confirm that VANet significantly improves re-ID accuracy, especially when the pair is observed from different viewpoints. Our method establishes the new state-of-the-art on two benchmarks.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 12; 2023: 6; 2024: 7; 2025: 0; 2026: 2.

45 papers.

Sort:

By area:

  1. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  2. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  3. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  4. 2021GiT: Graph Interactive Transformer for Vehicle Re-identificationcited by 49
  5. 2021Heterogeneous Relational Complement for Vehicle Re-identificationcited by 25
  6. 2021Multi-Scale Aligned Distillation for Low-Resolution Detectioncited by 24
  7. 2023Adaptive Sparse Pairwise Loss for Object Re-Identificationcited by 20
  8. 2022Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmarkcited by 17
  9. 2023Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identificationcited by 14
  10. 2021CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentationcited by 9
  11. 2022Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyondcited by 9
  12. 2024A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challengescited by 9
33 more
  1. 2024Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identificationcited by 9
  2. 2021Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systemscited by 8
  3. 2021AttributeNet: Attribute Enhanced Vehicle Re-Identificationcited by 6
  4. 2021ES-Net: Erasing Salient Parts to Learn More in Re-Identificationcited by 6
  5. 2022HSGNet: Object Re-identification with Hierarchical Similarity Graph Networkcited by 6
  6. 2021Improving Deep Metric Learning by Divide and Conquercited by 5
  7. 2022Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimizationcited by 5
  8. 2021Unsupervised Vehicle Re-Identification via Self-supervised Metric Learning using Feature Dictionarycited by 4
  9. 2022Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matchingcited by 4
  10. 2024Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Surveycited by 4
  11. 2021Rethinking Deep Contrastive Learning with Embedding Memorycited by 3
  12. 2021Hierarchical Image Classification with A Literally Toy Datasetcited by 2
  13. 2021DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identificationcited by 2
  14. 2021Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrievalcited by 2
  15. 2022Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrievalcited by 2
  16. 2022Style Variable and Irrelevant Learning for Generalizable Person Re-identificationcited by 2
  17. 2024DenoiseRep: Denoising Model for Representation Learningcited by 2
  18. 2021Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Camerascited by 1
  19. 2022Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identificationcited by 1
  20. 2023VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identificationcited by 1
  21. 2024Veri-Car: Towards Open-world Vehicle Information Retrievalcited by 1
  22. 2021Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identificationcited by 0
  23. 2021Copy and Paste method based on Pose for Re-identificationcited by 0
  24. 2022Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfercited by 0
  25. 2022HSADML: Hyper-Sphere Angular Deep Metric based Learning for Brain Tumor Classificationcited by 0
  26. 2022Enhanced Vehicle Re-identification for ITS: A Feature Fusion approach using Deep Learningcited by 0
  27. 2022Complete Solution for Vehicle Re-ID in Surround-view Camera Systemcited by 0
  28. 2023Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)cited by 0
  29. 2023A Novel Dual-pooling Attention Module for UAV Vehicle Re-identificationcited by 0
  30. 2023Beyond Sharing Weights in Decoupling Feature Learning Network for UAV RGB-Infrared Vehicle Re-Identificationcited by 0
  31. 2024Vessel Re-identification and Activity Detection in Thermal Domain for Maritime Surveillancecited by 0
  32. 2026VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Visioncited by 0
  33. 2026Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-Identificationcited by 0