Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.

Abstract: DETR-based methods have shown impressive performance in object detection tasks. The original DETR employs one-to-one sparse supervision, resulting in poor supervision capability. Denoising ...

NuML Studio is optimized for Windows and provides a "ready-to-use" version that does not require users to install Python or ...

HOI-DETR is a transformer-based framework for detecting hands, hand-held objects, and their interactions in images and video. Built on the Co-DETR architecture, it adds a lightweight interaction ...

This important work introduces an integrated open-source platform for behavioral acquisition and pose estimation that substantially improves the accessibility and speed of real-time animal tracking ...

Abstract: Underwater object detection has higher requirements of running speed and deployment efficiency for the detector due to its specific environmental challenges. Nonmaximum suppression (NMS) of ...

The debate over AI-driven fleet safety tools centers on whether technology can replace foundational driver training or only reinforce skills drivers have already learned through structured instruction ...

Axle counting is considered as one of the most advanced methods for monitoring track sections and detecting trains. Unlike traditional track circuits, which rely on the electrical conductivity of the ...