3 papers
cs.CV2025
Text2Traffic: A Text-to-Image Generation and Editing Method for Traffic Scenes
Feng Lv, Haoxuan Feng, Zilu Zhang +2
With the rapid advancement of intelligent transportation systems, text-driven image generation and editing techniques have demonstrated significant potential in providing rich, con…
cs.CV2025
RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment
Feng Lv, Guoqing Li, Jin Li +1
Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for…
cs.CV2024
RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision
Shuo Wang, Chunlong Xia, Feng Lv +1
RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense s…