There's also a monster-hunting Pathfinder class, but we're totally won over by the Dungeons and Dragons rival's new Daredevil ...

Abstract: Real-time semantic segmentation plays an important role in auto vehicles. However, most real-time small object segmentation methods fail to obtain satisfactory performance on small objects, ...

Abstract: Class-incremental learning (CIL) aims to preserve the knowledge of former classes during the updating process of category information. Existing CIL methods often employ a singular exemplar ...

If you want to compare with OVTrack and evaluate your own tracker's results on TAO TETA benchmark, Open-vocabulary MOT benchmark and BDD100K MOT and MOTS benchmarks. Please refer to the TETA repo for ...

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models ...

Water surface object detection is one of the most significant tasks in autonomous driving and water surface vision applications. To date, existing public large-scale datasets collected from websites ...