Aug 2026· The Visual Computer· Vol 42· 0 citations· 68 references
TL;DR
A unified empirical evaluation on the Market-1501, Occluded-DukeMTMC, and MSMT17 datasets is presented, revealing that latent feature-space refinement and semantic cross-modal alignment offer superior stability, scalability, and robustness compared to explicit pixel-level generation.
It is shown that feature-level enhancement methods achieve outstanding performance in occluded scenarios and good generalization in non-occluded scenarios, yielding the best overall effectiveness.
Yi-Tong Yu· Proceedings of the 4th Inter...· 0 citations
A novel Robust Modality Unified Learning framework (RMUL), consisting of a Robust Cross-modality Label Transfer (RCLT) method and Modality Unified Learning (MUL) module, which unifies cross-modality labels only for modality-shared instances while retaining the original labels for modality-specific ones.
Zhiyong Li, Wei Jiang, Haojie Liu et al.· International Journal of Mac...· 0 citations
A generative AI integrated multimodal ReID framework designed explicitly for robustness under missing cues and low latency deployment is proposed, with a cost aware early-exit cascade that prioritizes inexpensive, high confidence evidence and only triggers expensive modalities for ambiguous cases.
León Fernando, C. Dombawala, P. Hettigoda et al.· 0 citations
This approach introduces a Paired-Guided Consistency Rectification (PCR) module that utilizes strictly paired data as reliable anchors to dynamically calibrate the confidence of unpaired samples, effectively suppressing noise from inconsistent associations under mild-to-moderate corruptions.
A novel feature learning framework named DiffReID is proposed for object ReID that leverages a discriminative diffusion model to gradually learn identity-aware distributions and generate identity-invariant features.
Ying-Quan Wang, Ping-Ping Zhang, Dong Wang et al.· IEEE Transactions on Image P...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.