This repository is the official implementation of ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection For ease of use, we create a eval.sh script and a use case in the form of ...

Abstract: Low-light Object Detection (LOD) is a significant research field in computer vision. In some application fields of automatic driving, security monitoring and so on, it has great value and ...

Abstract: Traditional real-time object detection networks deployed in autonomous aerial vehicles (AAVs) struggle to extract features from small objects in complex backgrounds with occlusions and ...

Generative AI and robotics are moving us ever closer to the day when we can ask for an object and have it created within a few minutes. In fact, MIT researchers have developed a speech-to-reality ...

Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and ...