Research map / Vision-language and multimodal / Human and embodied modeling
Toward Re-Identifying Any Animal
Bingliang Jiao, Lingqiao Liu, Liying Gao, Ruiqi Wu, Guosheng Lin, PENG WANG, Yanning Zhang
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 category-specific adaptive visual prompts to static-prompt baseline (ablation) | UniReID · Wildlife-71 average | mAP: 39.7 -> 40.8 | Improved |
| add category-specific adaptive visual prompts to static-prompt baseline (ablation) | UniReID · Wildlife-71 average | CMC-1: 57.7 -> 59.1 | Improved |
| add text-guided attentive module on top of adaptive prompts (ablation) | UniReID · Wildlife-71 average | mAP: 40.8 -> 42.8 | Improved |
| add text-guided attentive module on top of adaptive prompts (ablation) | UniReID · Wildlife-71 average | CMC-1: 59.1 -> 62.6 | Improved |
| replace text-guided attention with self-attention on learnable vectors (ablation) | UniReID · Wildlife-71 average | CMC-1: 62.6 -> 60.1 | Hurt |
| self-attention module versus no attention (ablation) | UniReID · Wildlife-71 average | CMC-1: 59.1 -> 60.1 | Improved |
| use mismatched textual guidance (ablation) | UniReID · Wildlife-71 average | mAP: 42.8 -> 42.2 | Hurt |
| use general phrases instead of category-specific guidance (ablation) | UniReID · Wildlife-71 average | mAP: 42.8 -> 42.4 | Hurt |
| full tuning of CLIP instead of adaptive prompts (ablation) | UniReID · Wildlife-71 4 test categories | CMC-1 to CMC-5 | Hurt |
| norm tuning versus prompt tuning with static prompts (ablation) | UniReID · Wildlife-71 4 test categories | CMC | No clear effect |
| train on MSMT17 only instead of Wildlife-71 (ablation) | UniReID · Wildlife-71 average | mAP: 42.8 -> 32.1 | Hurt |
| train on VehicleID only instead of Wildlife-71 (ablation) | UniReID · Wildlife-71 average | mAP: 42.8 -> 31.5 | Hurt |
Closest papers by meaning
- Region-Aware Multimodal Interleaving for Animal Re-Identification (ECCV 2026 · similarity 0.91)
- Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling (AAAI 2026 · similarity 0.90)
- Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife (NeurIPS 2026 · similarity 0.86)
- Reconstructing Animals and the Wild (CVPR 2025 · similarity 0.86)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (NeurIPS 2024 · similarity 0.85)
- RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs (CVPR 2026 · similarity 0.84)
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.
