GitHub

JunweiLiang/Object_Detection_Tracking

This repository contains the code and models for object detection and tracking from the CMU DIVA system. Our system (INF & MUDSML) achieves the best performance on the ActEv leaderboard (Cached). If ...
GitHub

RF-DETR: Real-Time SOTA Object Detection, Instance Segmentation, and Keypoint Detection

RF-DETR is a real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow. Built on a DINOv2 vision transformer backbone, ...
LinkedIn

Beyond Boundaries: Open-Vocabulary vs Closed-World Object Detection

You might already be familiar with YOLO — the fast and efficient model that can find and label objects in images in real time. Maybe you've even heard of CLIP, which helps machines "understand" images ...
The Guardian

Reality cheque: we taught AI to spot the most used props this election. Here’s what it found

Hi-vis workwear and cute dogs have come to dominate politicians’ 2022 Australian federal election campaign photos, but giant cheques are out of fashion The novelty cheque has long been a mainstay of ...
Nature

Enhanced YOLOv5 network-based object detection (BALFilter Reader) promotes PERFECT filter-enabled liquid biopsy of lung cancer from bronchoalveolar lavage fluid (BALF)

Table 1 shows that CenterNet 26, EfficientDet 27 and YOLOv5 28 are frequently used in cancer diagnosis and achieve higher performance on MS COCO (a notable benchmark dataset) 29, which are higher than ...
Nature

An efficient single shot detector with weight-based feature fusion for small object detection

Object detection has been widely applied in various fields with the rapid development of deep learning in recent years. However, detecting small objects is still a challenging task because of the ...