Research map / Label-efficient and robust learning / Recognition and long-tail
Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use PVEN instead of PRN | vehicle re-identification · VehicleID small, medium, and large | CMC@1: 3.6%+ | Helped |
| use PVEN instead of PRN | vehicle re-identification · VeRi776 | mAP: 5.2% | Helped |
| use PVEN instead of PRN | vehicle re-identification · VeRi776 | CMC@1: 1.3% | Helped |
| use PVEN instead of FDA-Net | vehicle re-identification · VERI-Wild small, medium, and large | mAP: 47.4%, 47.2%, and 46.9% | Helped |
| add the local view-aware feature branch (ablation) | PVEN · VehicleID | CMC@1: 0.796 -> 0.847 | Helped |
| add the local view-aware feature branch (ablation) | PVEN · VehicleID | CMC@5: 0.937 -> 0.970 | Helped |
| add common-visible attention (ablation) | PVEN local feature branch · VehicleID | CMC@1: 0.766 -> 0.847 | Helped |
| add common-visible attention (ablation) | PVEN local feature branch · VehicleID | CMC@5: 0.900 -> 0.970 | Helped |
| use vehicle parsing instead of evenly splitting images vertically (ablation) | PVEN · VeRi776 | mAP: 0.775 -> 0.795 | Helped |
| include local view-aware distance alongside global distance (ablation) | PVEN · VeRi776 | mAP: 0.787 -> 0.795 | Helped |
| set local-distance weight λ2 to 0.3 instead of 0 (ablation) | PVEN · VeRi776 | mAP: 0.787 -> 0.794 | Helped |
| set local-distance weight λ2 to 0.7 instead of 0 (ablation) | PVEN · VeRi776 | mAP: 0.787 -> 0.794 | Helped |
Closest papers by meaning
- Learning Coarse-to-Fine Structured Feature Embedding for Vehicle Re-Identification (AAAI 2018 · similarity 0.90)
- Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification (CVPR 2018 · similarity 0.89)
- CLIP-driven View-aware Prompt Learning for Unsupervised Vehicle Re-identification (AAAI 2025 · similarity 0.88)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · similarity 0.87)
- Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception (AAAI 2024 · similarity 0.82)
- DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning (CVPR 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.