YOLO Series
The YOLO (You Only Look Once) series of object detection models focuses on achieving real-time performance with high accuracy. Current research emphasizes improving YOLO's capabilities through architectural modifications (e.g., incorporating attention mechanisms, novel feature fusion techniques), adapting it for specialized tasks (e.g., medical image analysis, action recognition, and pavement damage detection), and enhancing its robustness in challenging conditions (e.g., low light, occlusion, and heavy rain). This work has significant implications for various fields, including autonomous driving, medical imaging, and infrastructure monitoring, by enabling faster and more accurate object detection in real-world applications.
Papers
April 14, 2023
February 14, 2023
November 23, 2022
November 12, 2022
September 26, 2022
August 3, 2022
November 16, 2021