AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification

Xingguo Xu, Zhanyu Liu, Weixiang Zhou, Yuansheng Gao, Junjie Cao, Yuhao Wang, Jixiang Luo, Dell Zhang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modal object re-identification · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add SAM-mask-guided feature modulation (SFM) (ablation)multi-modal ReID baseline · RGBNT201mAP: 70.3 -> 76.1Improved
add Semantic Token Reallocation (STR) (ablation)baseline + SFM · RGBNT201mAP: 76.1 -> 78.1Improved
add Cross-Modal Hypergraph Interaction (CHI) (ablation)baseline + SFM + STR · RGBNT201mAP: 78.1 -> 81.2Improved
fuse modalities with MLP instead of CHI (ablation)STMI · RGBNT201mAP: 78.1 -> 78.0No clear effect
fuse modalities with self-attention instead of CHI (ablation)STMI · RGBNT201mAP: 78.1 -> 78.4No clear effect
use layer-wise SFM parameters shared across heads instead of one shared set (ablation)SFM · RGBNT201mAP: 77.2 -> 81.2Improved
apply SFM to all layers instead of only early layers (ablation)SFM · RGBNT201mAP: 73.5 -> 81.2Improved
apply SFM to all layers instead of only late layers (ablation)SFM · RGBNT201mAP: 76.7 -> 81.2Improved
use head-wise SFM parameters (ablation)SFM · RGBNT201mAP: 81.2 -> 77.1Hurt
add small random mask perturbation for background tokens (ablation)SFM · RGBNT201mAPMixed
use more than four learnable query tokens (ablation)STR · RGBNT201mAPNo clear effect
STMI vs IDEA on RGBNT100 Rank-1 and RGBNT201 Rank-10STMI · RGBNT100 / RGBNT201Rank-1 / Rank-10: RGBNT201 R-10 93.3 (IDEA) vs 91.6Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy