Qingyi Gu

最新

• MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
• RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
• Patch Similarity Aware Data-Free Quantization for Vision Transformers
• Efficient MSPSO Sampling for Object Detection and 6-D Pose Estimation in 3-D Scenes
• Calibration and Measurement of Large Distortion Binocular Camera Based on Fully Connected Neural Network
• Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization
• Natural Scene Facial Expression Recognition with Dimension Reduction Network
• Segmentation of Complex Object based on A Standardization Coding Method
• Natural Scene Facial Expression Recognition based on Differential Features
• Multi-loss-aware Channel Pruning of Deep Networks
• Cluster Regularized Quantization for Deep Networks Compression
• Motion-blur-free High-speed Video Shooting with Frame-timing Control
• 12,000-fps Multi-object Detection using HOG Descriptor and SVM Classifier
• Real-Time Vibration Source Tracking using High-Speed Vision
• Motion-Blur-Free High-Speed Video Shooting Using a Resonant Mirror
• Position and Inclination Control of a Passive Disk Based on Cyclic Motion Generation
• A High-Frame-Rate High Dynamic Range Imaging from Virtual Multi-Thread Automatic Exposures
• Super High-Speed Vision Platform that can Process 1024x1024 Images in Real Time at 12500 Fps
• Motion-blur-free Video Recording under Microscope Using High-speed Intermittent Tracking
• Motion-blur-free Video Recording under Microscope Using High-speed Intermittent Tracking
• Control Scheme of Nongrasping Manipulation Based on Virtual Connecting Constraint
• An Intermittent Frame-by-frame Tracking Camera for Motion-blur-free Video Shooting
• Blink-spot Projection Method for Fast Three-dimensional Shape Measurement
• Realization of Flower Stick Rotation using Robotic Arm
• Motion-blur-free Microscopic Video Shooting based on Frame-by-frame Intermittent Tracking
• A Fast 3D Shape Scanner using Two HFR Camera-projector Systems
• Real-time Flow-rate Control System for Cell Analysis
• Real-time Optical Image Stabilization using High Frame Rate Video Sequence at 500 Fps
• A Scheme for Manipulating a Passive Object using an Active Plate
• Robot-mounted 500-fps 3-D Shape Measurement using Motion-compensated Coded Structured Light Method
• A Fast 3-D Shape Measurement Method for Moving Object
• Cyclic Motion Design and Analysis for a Passive Object Manipulation using an Active Plate
• High-frame-rate Structured Light 3-D Vision for Fast Moving Objects
• A Fast Multi-camera Tracking System with Heterogeneous Lenses
• Fast 3-D Shape Measurement using Blink-dot Projection
• Real-time Feature-based Video Mosaicing at 500 Fps
• Dynamics-based Stereo Visual Inspection using Multidimensional Modal Analysis
• Real-time Modal Analysis of Shell-shaped Objects using High-frame-rate Structured-light-based Vision
• 500-fps Face Tracking System
• Color-histogram-based Tracking at 2000 Fps
• A Fast Multiobject Extraction Algorithm based on Cell-based Connected Components Labeling
• 2000 FPS Real-time Target Tracking Vision System Based on Color Histogram
• Patch-Wise Mixed-Precision Quantization of Vision Transformer
• G-Head: Gating Head for Multi-task Learning in One-stage Object Detection
• A Flexible Calibration Algorithm for High-speed Bionic Vision System based on Galvanometer
• DLA: Dynamic Label Assignment for Accurate One-stage Object Detection
• Efficient Center Voting for Object Detection and 6D Pose Estimation in 3D Point Cloud
• An Efficient Watershed Algorithm for Preprocessed Binary Image
• Review of some advances and applications in real-time high-speed vision: Our views and experiences
• A Full-pixel Optical Flow System using a GPU-based High-frame-rate Vision
• LOC-Based High-throughput Cell Morphology Analysis System
• Real-time Image Mosaicing System Using a High-frame-rate Video Sequence
• Real-time LOC-based Morphological Cell Analysis System using High-speed Vision
• Rapid Vision-based Shape and Motion Analysis System for Fast-flowing Cells in a Microchannel
• Simultaneous Vision-based Shape and Motion Analysis of Cells Fast-flowing in a Microchannel
• A Fast Color Tracking System with Automatic Exposure Control
• Fast Tracking System for Multi-colored Pie-shaped Markers
• Fast Tracking System for Multi-colored Pie-shaped Markers
• High-frame-rate Tracking of Multiple Color-patterned Objects
• Fast FPGA-based Multiobject Feature Extraction
• 2000-fps Multi-object Tracking based on Color Histogram
• 2000-FPS Multi-object Extraction based on Cell-based Labeling
• 2000 FPS Real-time Vision System with High-frame-rate Video Recording
• DCIFPN: Deformable cross-scale interaction feature pyramid network for object detection
• Region Probability Map-Guided Fast Wide-Area Multiobject Detection
• CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection
• Mechanical Particle Filter Based Active Vision System for Fast Wide-Area Multi-Object Detection
• PWSNAS: Powering Weight Sharing NAS With General Search Space Shrinking Framework
• Improving One-Shot NAS with Shrinking-and-Expanding Supernet
• Angle-based Search Space Shrinking for Neural Architecture Search
• An Ultra-High-Speed Object Detection Method with Projection-based Position Compensation
• A High-speed Vision System with Multithread Automatic Exposure Control for High-dynamic-range Imaging
• Temporal Action Detection with Dynamic Weights based on Curriculum Learning
• Boosting Semi-Supervised Face Recognition with Raw Faces
• Class-wise boundary regression by uncertainty in temporal action detection
• An Ultra-High-Speed Object Detection Method with Projection-based Position Compensation
• An Ultra-High-Speed Object Detection Method with Projection-based Position Compensation
• A Hardware-Oriented Algorithm for Ultra-High-Speed Object Detection
• A Visual-Feedback-Based Active Light-Section 3-D Reconstruction Method for Moving Objects
• A Visual-Feedback-Based Active Light-Section 3-D Reconstruction Method for Moving Objects
• CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection
• Hardware-Oriented Algorithm for High-Speed Laser Centerline Extraction Based on Hessian Matrix
• Qft: Quantized full-parameter tuning of llms with affordable resources
• CacheQuant: Comprehensively Accelerated Diffusion Models
• DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
• K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences
• DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
• LLM Inference Unveiled: Survey and Roofline Model Insights
• RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization
• EDA-DM: Enhanced distribution alignment for post-training quantization of diffusion models
• PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
• I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
• BinaryViT: Towards Efficient and Accurate Binary Vision Transformers
• Rethinking Prediction Alignment in One-stage Object Detection
• Dual-Discriminator Adversarial Framework for Data-Free Quantization