Research map / Vision-language and multimodal / Cross-modal learning
Incentive Noise and Structural Prior Infusion for Multi-Modal Object Re-Identification
Weixiang Zhou, Yuhao Wang, Xingguo Xu, Cong Wang, Weizhen Zhou, Zhixun Su, Jinshan Pan
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 CASF (ablation) | CLIP baseline · RGBNT201 | mAP: 70.3 -> 76.5 | Improved |
| add SPA (ablation) | Baseline + CASF · RGBNT201 | mAP: 76.5 -> 78.6 | Improved |
| add SCM (ablation) | Baseline + CASF + SPA · RGBNT201 | mAP: 78.6 -> 80.6 | Improved |
| add CASF (ablation) | CLIP baseline · MSVR310 | mAP: 40.4 -> 55.8 | Improved |
| add SPA (ablation) | Baseline + CASF · MSVR310 | mAP: 55.8 -> 61.1 | Improved |
| add SCM (ablation) | Baseline + CASF + SPA · MSVR310 | mAP: 61.1 -> 65.0 | Improved |
| use task-aware pi-noise instead of Gaussian noise (ablation) | SCM · RGBNT201 | mAP: 76.1 -> 80.6 | Improved |
| use conditioned pi-noise instead of dropout (ablation) | SCM · RGBNT201 | mAP: 75.7 -> 80.6 | Improved |
| use gated cross-attention instead of standard cross-attention (ablation) | SCM · RGBNT201 | mAP: 79.4 -> 80.6 | Improved |
| initialize prompts with DINOv3 instead of randomly (ablation) | SPA · RGBNT201 | mAP: 78.0 -> 80.6 | Improved |
| use MoE routing instead of linear fusion (ablation) | CASF · RGBNT201 | mAP: 78.5 -> 80.6 | Improved |
| feed noise-enhanced global tokens to MoE instead of raw tokens (ablation) | CASF · RGBNT201 | mAP: 78.6 -> 80.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- IDEA — IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification (CVPR 2025) · better on 5 of 5 shared results
- MambaPro — MambaPro: Multi-Modal Object Re-identification with Mamba Aggregation and Synergistic Prompt (AAAI 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification (NeurIPS 2025 · similarity 0.89)
- IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification (CVPR 2025 · similarity 0.88)
- Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion (ICLR 2025 · similarity 0.87)
- Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification (CVPR 2024 · similarity 0.87)
- LoMo: Local Modality Substitution for Deeper Vision-Language Fusion (NeurIPS 2026 · similarity 0.86)
- Multi-Modal Object Re-identification via Sparse Mixture-of-Experts (ICML 2025 · similarity 0.86)
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.
