A complementary dual-backbone transformer extracting and fusing weak cues for object detection in extremely dark videos

Open Webpage

Bo Zhang, Jinli Suo, Qionghai Dai

Published: 01 Jan 2023, Last Modified: 10 Oct 2025Inf. Fusion 2023EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Dual-backbone structure strengthens feature extraction capability for low-light images/videos.•Powerful temporal feature aggregation fuses information of multiple frames in dark videos.•Illumination-aware feature fusion adapts to dark data with high dynamic range and variant darkness levels.•Overall hybrid-backbone model achieves superior performance to existing works for object detection in extremely dark videos.