- Rating
- 2
- Confidence
- 2(−1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes JESD-ReID to reduce cross-modal discrepancies while preserving complementary information for multi-modal object re-identification. Shared semantic observations are jointly reconstructed from one latent code through constrained modality-conditioned dictionaries. The reconstructed components receive low-volume regularization, while token residuals receive relational optimal transport. Gated modality-role experts and deformable aggregation produce the retrieval descriptor. Experiments on RGBNT201, RGBNT100, and MSVR310 report 82.4%, 88.0%, and 66.6% mAP, with component and property-assignment ablations.
Critical strengths
-
The paper addresses a relevant problem: reducing modality discrepancy while retaining complementary information. JESD gives the decomposition an explicit shared-code formulation, while allowing the reconstructed components to differ across sensors through constrained dictionaries.
-
The experiments cover both person and vehicle ReID. The component ablations show consistent improvements, Table 4 supports the proposed regularizer assignment, and Table 6 confirms that combining the two components improves retrieval. The results are competitive, particularly on MSVR310 dataset.
Critical weaknesses
-
The advantage of the shared-code criterion over existing decomposition strategies is not sufficiently established. Table 3 adds JESD as a whole, leaving unclear whether the gains come from sharing the code or from the surrounding observation and reconstruction design. This limits the evidence for the paper's main contribution.
-
The contribution of additional inputs and evaluation choices is unclear. Captions and camera metadata are used during both training and inference, and reported scores also use test augmentation. Image-only and single-view results are needed to clarify how much of the improvement comes from the proposed architecture.
Questions for authors
-
Could the authors include more methods from 2026 to better support the claimed advantage over the state of the art?
-
How does JESD compare with independently estimated modality codes when the remaining architecture, supervision, and regularization strength are matched?
-
How does relational transport compare with feature-distance transport under the same JESD and OT settings, with comparable tuning of the loss weight and transport temperature?
-
What are the separate contributions of the modality-role experts and learned deformable sampling when the remaining components are unchanged?
-
How sensitive is retrieval performance to the ridge coefficient when the shared-slot number and dictionary-adaptation rank are fixed?
As of now, I have not received a rebuttal. If there is no rebuttal, I will keep my negative score.