High performance RGB-Thermal Video Object Detection via hybrid fusion with progressive interaction and temporal-modal difference

Qishun Wang, Zhengzheng Tu, Chenglong Li, Jin Tang

Abstract

Highlights•A hybrid fusion strategy network for RGB-Thermal video object detection.•An early strategy for reducing modal disparities.•A novel differential method for modeling multimodal and temporal information.•The proposed PTMNet achieves SOTA performance on the VT-VOD50 dataset.
BibTeX
@article{wang2025high,
  author = {Qishun Wang and Zhengzheng Tu and Chenglong Li and Jin Tang},
  title = {{High performance RGB-Thermal Video Object Detection via hybrid fusion with progressive interaction and temporal-modal difference}},
  journal = {Information Fusion},
  year = {2025},
  doi = {10.1016/j.inffus.2024.102665},
}

Loading related content...

Figure