Abstract: Traditional object detection requires extensive annotation, consuming considerable time and manpower. In recent years, semi-supervised object detection (SSOD) methods, which utilize a blend ...
Memoria-Bench is a next-generation benchmark for evaluating model memory capabilities in agent settings. It is built around three major domains: deep research, code agents, and tabular tasks. The ...
Abstract: In low-light conditions, the detection scene can be harsh, some fundamental image features of the target to be lost, which can result in the disappearance of essential visual characteristics ...