Research map / Label-efficient and robust learning / Recognition and long-tail
Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification
Wajahat Khalid, Bin Liu, Xulin Li, Muhammad Waqas, Muhammad Sher Afgan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add Patch-Level RotateMix (PLRM) (ablation) | ViT-B baseline · CARGO A<->G | Rank1: 43.13 -> 48.12 (+4.99) | Improved |
| add VIAL loss (ablation) | ViT-B baseline · CARGO A<->G | Rank1: 43.13 -> 50.63 (+7.5) | Improved |
| combine PLRM with VIAL (ablation) | ViT-B baseline · CARGO A<->G | Rank1: 50.63 -> 51.25 | Improved |
| combine PLRM with VIAL (ablation) | ViT-B baseline · CARGO ALL | Rank1: 65.38 -> 65.71 | Improved |
| use PLRM instead of random rotation (ablation) | ViT-B baseline · CARGO A<->G | Rank1: 46.25 -> 48.12 (+1.87) | Improved |
| use PLRM instead of PatchShuffle (ablation) | ViT-B baseline · CARGO A<->G | Rank1: 46.88 -> 48.12 (+1.24) | Improved |
| add plain angular loss (ablation) | ViT-B baseline · CARGO A<->G | Rank1: 43.13 -> 46.88 (+3.75) | Improved |
| add view-invariant penalty to angular loss (ablation) | VIAL · CARGO A<->G | Rank1: 46.88 -> 49.38 (+2.5) | Improved |
| add hard negative mining (HNM) to VIAL (ablation) | VIAL · CARGO A<->G | Rank1: 49.38 -> 50.63 (+1.25) | Improved |
| add hard negative mining (HNM) to VIAL (ablation) | VIAL · CARGO ALL | mINP: 41.94 -> 43.27 | No clear effect |
| vary beta from 5 to 25 (ablation) | VIAL · CARGO ALL | Rank1/mINP | Hurt |
| vary lambda over 0.1-0.9 (ablation) | VIAL · CARGO ALL | Rank1/mINP | Mixed |
Closest papers by meaning
- MCVL: Multi-Space Cross-View Learning for Aerial-Ground Person Re-Identification (ECCV 2026 · similarity 0.94)
- AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification (CVPR 2025 · similarity 0.93)
- SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks (CVPR 2025 · similarity 0.92)
- GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification (NeurIPS 2025 · similarity 0.92)
- View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network (CVPR 2024 · similarity 0.91)
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.85)
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.
