This article summarizes a computer‑vision salon where Dr. Ji Yongnan explains imaging pipelines, traditional feature‑based methods, deep‑learning breakthroughs, Tencent Cloud AI services, real‑world case studies, and answers audience questions about machine‑vision versus computer‑vision and data‑scarcity challenges.
This article surveys the evolution of object detection models—comparing one‑stage and two‑stage approaches, their performance trade‑offs, and recent state‑of‑the‑art methods—while also outlining key concepts and breakthroughs in natural language processing, highlighting the impact of deep‑learning models such as BERT.
This article provides an extensive review of deep learning techniques applied to computer vision, covering the evolution of CNN architectures, image and video processing tasks, 2.5‑D and 3‑D reconstruction, object detection, segmentation, tracking, SLAM, and various practical applications such as AR, content retrieval, and autonomous driving.
This tutorial walks through extending a deep‑learning object detector to process live video streams using OpenCV and Python, covering setup, command‑line arguments, model loading, frame‑by‑frame detection, drawing bounding boxes, FPS measurement, and performance tips.
This article introduces the Intelligent News Formatter, an AI‑driven system that tackles news‑app list‑image problems by using face detection, object detection, deep‑learning based cropping, image quality filtering, and similarity removal to automatically produce aesthetically pleasing and information‑rich thumbnails.
The article summarizes Jifeng Dai's 2018 AI Pioneer talk on recent object‑detection breakthroughs, detailing R‑FCN and its extensions, Deformable ConvNets, video object detection techniques, and concluding remarks on remaining challenges in large‑scale and mobile vision.
This article reviews major deep‑learning object detection approaches—including one‑stage YOLO and SSD and two‑stage RCNN, Fast RCNN, and Faster RCNN—then provides a step‑by‑step explanation of Faster RCNN’s architecture, region‑proposal network, RoI pooling, loss functions, and sample PyTorch code.
This survey reviews deep‑learning‑based object detection, tracing evolution from R‑CNN to modern two‑stage (Faster R‑CNN) and one‑stage (YOLO, SSD) models, discusses enhancements for scale variance, small‑object and domain‑shift challenges—including logo detection pipelines, PANet, temporal action localization, knowledge‑distillation training, and extensive speed‑accuracy trade‑off analyses to guide practitioners.
The article reviews deep learning object detection solutions: small object detection via FPN and TDM, irregular shapes via deformable convolution, sample imbalance via focal loss and cascade methods, occlusion handling with Soft‑NMS and RRC, large‑batch training using MegDet, relationship modeling with Relation Networks, and network improvements such as DetNet, RefineDet, Pelee, and RFBNet.
This survey reviews two‑stage and one‑stage deep learning object detection methods—from early R‑CNN and OverFeat to modern Faster R‑CNN, Mask R‑CNN, SSD, and YOLO variants—detailing their architectural advances, training strategies, speed‑accuracy trade‑offs, and benchmark performance for researchers and industry practitioners.
This article reviews the evolution of visual object detection, explaining traditional region‑based approaches, the rise of deep‑learning two‑stage frameworks such as R‑CNN, Fast R‑CNN and Faster R‑CNN, and the faster one‑stage models like Overfeat, YOLO, SSD and RetinaNet, together with their design choices, training strategies and loss functions.
This article provides a comprehensive technical overview of Alipay's AR platform, covering AR fundamentals, classification, the platform's layered architecture, NFT and AI‑based recognition pipelines, client‑server processing, performance metrics, and recruitment information for interested engineers.
This guide walks you through extending a deep‑learning object detection project to process live video streams using OpenCV, Python, and the VideoStream class, covering environment setup, command‑line arguments, model loading, frame‑by‑frame detection, FPS measurement, and performance‑boosting tips.
Alibaba’s AI breakthroughs—from a foot‑scanning shopping demo that lets a Google engineer instantly find matching shoes, to a record‑setting vehicle detection model on KITTI and world‑leading OCR for real‑time image review—showcase the power and commercial potential of modern computer‑vision research.
Mobile image search has become a critical user demand, and since its 2014 launch, Alibaba’s Paizhi Tao has evolved through multiple iterations to a robust AI-driven pipeline comprising category prediction, object detection, deep and local image feature extraction, scalable retrieval indexing, and relevance-based ranking.