Pith. sign in

REVIEW 1 cited by

Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1901.02645 v2 pith:74M6FKIA submitted 2019-01-09 cs.CV

classification cs.CV
keywords alignedmodalitiesmultispectraldatadifferentfeaturemethodregion
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position shift problem, i.e. the color-thermal image pairs are not strictly aligned, making one object has different positions in different modalities. In deep learning based methods, this problem makes it difficult to fuse the feature maps from both modalities and puzzles the CNN training. In this paper, we propose a novel Aligned Region CNN (AR-CNN) to handle the weakly aligned multispectral data in an end-to-end way. Firstly, we design a Region Feature Alignment (RFA) module to capture the position shift and adaptively align the region features of the two modalities. Secondly, we present a new multimodal fusion method, which performs feature re-weighting to select more reliable features and suppress the useless ones. Besides, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns of different devices and system settings. Finally, since our method depends on a new kind of labelling: bounding boxes that match each modality, we manually relabel the KAIST dataset by locating bounding boxes in both modalities and building their relationships, providing a new KAIST-Paired Annotation. Extensive experimental validations on existing datasets are performed, demonstrating the effectiveness and robustness of the proposed method. Code and data are available at https://github.com/luzhang16/AR-CNN.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

    cs.CV 2025-07 conditional novelty 6.0 of 10

    M-SpecGene is a Siamese masked-autoencoder foundation model for RGB-thermal vision, trained on the RGBT550K dataset with a GMM-CMSS progressive masking strategy, and evaluated on four downstream tasks.

Pith tools