MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection

arXiv:2403.15209v1 Announce Type: new
Abstract: Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in obvious cases, especially due to the modality bias learned from statistically biased datasets. From these problems, we anticipate that maybe understanding the complementary information itself is difficult to achieve from vision-only models. Accordingly, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework, which incorporates Large Language Models (LLMs) …

abstract applications arxiv bias cases cs.cv current datasets detection fusion however information language modal multi-modal pedestrian pedestrians type