DGPE: A Dual-Stream Geometric-Aware Positional Encoding for Transformer-based Object Detection
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Access"
DOI: 10.1109/access.2025.3640410
Abstract: Accurately modeling complex spatial relationships is a pivotal challenge for Transformer-based object detectors, as existing models often rely on static positional encodings that fail to capture dynamic, real-world scene layouts. To address this issue, this… read more here.
Keywords: dgpe; transformer based; geometric aware; stream geometric ... See more keywords