Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification
cs.CV
Submitted: 2026-01-29
Updated: 2026-02-25
Code: https://github.com/kailashhambarde/GeoReID
Terminology
Sources
- Person Re-identification: Past, Present and Future
- PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification
- DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition
- SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification
- GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
- Dynamic Token Selection for Aerial-Ground Person Re-Identification
- LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs