Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object ...

Humans can recognize novel objects in this image despite having never seen them before. “Is it possible to learn open-world (novel) object proposals?” In this paper we propose Object Localization ...

Abstract: Object tracking has been one of the most important and active research areas in the field of computer vision. A large number of tracking algorithms have been proposed in recent years with ...

Abstract: Tiny object detection in the field of remote sensing has always been a challenging and interesting topic. Despite many researchers working on this problem, it has not been well-solved due to ...