Metraipolis › archive › dc_fdea330b3f0d

MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering — arXiv:2608.15096

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15096
License (as archived)
CC0-1.0
Archived
2026-10-19T02:19:19.883Z
SHA-256 of the archived text
4397e362ee1cfc96e118773953d954c55333efa62c10d600a12fb5c5d4d71261
Stable URL of this page
https://metraipolis.com/documento/dc_fdea330b3f0d

How to cite

MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering — arXiv:2608.15096 — arXiv (en), https://arxiv.org/abs/2608.15096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdea330b3f0d (Metraipolis archive dc_fdea330b3f0d, sha256 4397e362ee1cfc96e118773953d954c55333efa62c10d600a12fb5c5d4d71261)
BibTeX
@misc{dcfdea330b3f0d,
  title = {MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering — arXiv:2608.15096},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15096},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdea330b3f0d; sha256 4397e362ee1cfc96e118773953d954c55333efa62c10d600a12fb5c5d4d71261},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-modal object re-identification (Re-ID) aims to facilitate cross-camera object retrieval in complex environments by leveraging complementary information from visual (e.g., RGB, NIR, TIR) and textual modalities. However, existing approaches often lack principled feature disentanglement and coherent multi-modal integration, leading to entangled representations that introduce cross-modal conflicts, obscure discriminative cues, and suffer distribution shift under modality-missing conditions. To tackle these challenges, we propose MODAL, a novel multi-modal object re-identification framework, grounded in coupled sparse coding theory and differential suppression principles. A core component of MODAL is a Multi-modal Feature Sparse Decoupling module, developed in a model-driven deep unrolling manner based on multi-modal coupled sparse coding. It explicitly decomposes multi-modal features into uni-modal specific, bi-modal and tri-modal shared representations, thereby achieving more transparent and effective feature disentanglement. Benefiting from the principled feature disentanglement, MODAL naturally mitigates performance degradation in incomplete-modality scenarios via a Modality-Aware Subspace Activation that selectively activates only the consistently shared subspaces. Moreover, we propose a Text-Image Differential Filtering module that leverages coarse-grained textual semantics to adaptively suppress task-irrelevant responses in the decoupled visual representations, thereby enhancing discriminative information. Extensive experiments on four datasets demonstrate that MODAL achieves state-of-the-art performance with superior transparency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in eess.IV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2608.15096 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T01:56:52.993Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).