SOTAVerified

Real-Time Object Detection

Real-Time Object Detection is a computer vision task that involves identifying and locating objects of interest in real-time video sequences with fast inference while maintaining a base level of accuracy.

This is typically solved using algorithms that combine object detection and tracking techniques to accurately detect and track objects in real-time. They use a combination of feature extraction, object proposal generation, and classification to detect and localize objects of interest.

( Image credit: CenterNet )

Papers

Showing 3140 of 259 papers

TitleStatusHype
Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsCode2
Objects as PointsCode2
Focal Loss for Dense Object DetectionCode2
RT-DATR:Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature LearningCode1
Optimizing Edge Offloading Decisions for Object DetectionCode1
DART: An Automated End-to-End Object Detection Pipeline with Data Diversification, Open-Vocabulary Bounding Box Annotation, Pseudo-Label Review, and Model TrainingCode1
MODIPHY: Multimodal Obscured Detection for IoT using PHantom Convolution-Enabled Faster YOLOCode1
Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOCode1
HIC-YOLOv5: Improved YOLOv5 For Small Object DetectionCode1
BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor DetectionCode1
Show:102550
← PrevPage 4 of 26Next →

No leaderboard results yet.