AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching

X X Xu, Shuhao Zhan, Wei Liu, Zheng Wang, Kui Jiang, Chia‐Wen Lin

IJCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 0 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 grayscale conversion only in Stage 1 before RGB training (Gray-RGB vs RGB) (ablation)MAMT · SYSU-VIMI (0.1), VIMCmAP: 55.79 -> 60.34 mAP, Rank-1 95.09 -> 96.37Improved
use grayscale images for all training (Gray vs RGB) (ablation)MAMT · SYSU-VIMI (0.1), VIMCmAP: 55.79 -> 34.69 mAP, a decrease of 21.10%Hurt
add visible-specific branch (MAM) (ablation)MAMT with ViT · SYSU-VIMI (0.1), VIMCRank-1/mAP: 94.29 -> 95.33 Rank-1, 56.32 -> 57.73 mAPImproved
add infrared-specific branch (MAM) (ablation)MAMT with ViT · SYSU-VIMI (0.1), VIMCRank-1/mAP: 94.29 -> 94.96 Rank-1, 56.32 -> 56.99 mAPImproved
add both visible and infrared branches (ablation)MAMT with ViT · SYSU-VIMI (0.1), VIMCRank-1/mAP: 94.29 -> 96.37 Rank-1, 56.32 -> 59.39 mAPImproved
add divergence loss L_D on top of both branches (ablation)MAMT with ViT · SYSU-VIMI (0.1), VIMCmAP: 59.39 -> 60.34 mAP, Rank-1 maintained at 96.37Improved
add all MAM modules and L_D (ResNet backbone) (ablation)MAMT with ResNet · SYSU-VIMI (0.1), VIMCRank-1/mAP: 89.20 -> 92.76 Rank-1, 37.35 -> 41.59 mAPImproved
add all MAM modules and L_D (ViT backbone) (ablation)MAMT with ViT · SYSU-VIMI (0.1), VIMCRank-1/mAP: 94.29 -> 96.37 Rank-1, 56.32 -> 60.34 mAPImproved
use one unified model instead of multi-model ensemble of AGWMAMT · VIMI-ReIDmemory and time: 20G -> 12G memory, 8h -> 5h trainingImproved
use MAMT instead of all-in-one IRM under VIMCMAMT vs IRM · VIMCmAP: 16.50 -> 60.34 mAPImproved
MAMT vs second-best PMT under VIMC on SYSU-VIMI (0.5)MAMT · SYSU-VIMI (0.5), VIMCRank-1/mAP: Rank-1 99.31 -> 98.91, mAP 67.24 -> 69.50Mixed
MAMT vs second-best on RegDB-VIMI (0.5) under VIMCMAMT · RegDB-VIMI (0.5), VIMCmAP: 84.46 -> 93.52 mAPImproved

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