Brief Program Keynote Invitation Keynote PRCV & DICTA 2022 Joint Session Thematic Forum Women in Science Forum Tutorial Doctoral Consortium The current and future machine imaging for medical robots Papers
Accepted Papers







Accepted Papers

Paper ID Paper Title
0009 Attention-based Fusion of Directed Rotation Graphs for Skeleton-based Dynamic Hand Gesture Recognition
0010 Cloth-Aware Center Cluster Loss for Cloth-Changing Person Re-identification
0015 Multi-View Geometry Distillation for Cloth-changing Person ReID
0018 Thangka Mural Line Drawing Based on Dense and Dual-Residual Architecture
0022 A high-order tensor completion algorithm based on Fully-Connected Tensor Network weighted optimization
0023 Dirt Detection and Segmentation Network for Autonomous Washing Robots
0030 Video Deraining via Temporal Discrepancy Learning
0036 ED-AnoNet: Elastic Distortion-Based Unsupervised Network for OCT Image Anomaly Detection
0042 Architecture Colorizing via Instance Segmentation
0044 Handwritten Mathematical Expression Recognition via GCAttention-Based Encoder and Bidirectional Mutual Learning Transformer
0048 Efficient Channel Pruning via Architecture-Guided Search Space Shrinking
0055 Learning to Cluster Faces with Mixed Face Quality
0057 TAFDet: A Task Awareness Focal Detector for Ship Detection in SAR Images
0060 Momentum Distillation Improves Multimodal Sentiment Analysis
0065 Multi-priors Guided Dehazing Network Based on  Knowledge Distillation
0067 EFG-Net: A Unified Framework for Estimating Eye Gaze and Face Gaze Simultaneously
0072 Category-oriented Adversarial Data Augmentation via Statistic Similarity for Satellite Images
0075 BiDFNet: Bi-decoder and Feedback Network for Automatic Polyp Segmentation with Vision Transformers
0076 DLMP-Net: a dynamic yet lightweight multi-pyramid network for crowd density estimation
0079 A Multi-scale Convolutional Neural Network Based on Multilevel Wavelet Decomposition for Hyperspectral Image Classification
0081 CHENet: Image to Image Chinese Handwriting Eraser
0084 JVLDLoc: a Joint Optimization of Visual-LiDAR Constraints and Direction Priors for Localization in Driving Scenario
0090 Self-Supervised Adaptive Kernel Nonnegative Matrix Factorization
0095 A Stage-Mutual-Affine Network for Single Remote Sensing Image Super-Resolution
0096 High Spatial Resolution Remote Sensing Imagery Classification Based on Markov Random Field Model Integrating Granularity and Semantic Features
0099 A Single-pathway Biomimetic Model for Potential Collision Prediction
0104 Synthesizing Counterfactual Samples for Overcoming Moment Biases in Temporal Video Grounding
0106 FundusGAN: A One-Stage Single Input GAN for Fundus Synthesis
0109 DIT-NET: Joint Deformable Network and Intra-class Transfer GAN for cross-domain 3D Neonatal Brain MRI segmentation
0110 MSDNet:Multi-scale Dense Networks for Salient Object Detection
0112 Identification method for rice pests with small sample size problem combining  deep learning and metric learning
0119 Classification of sMRI Images for Alzheimer's Disease by Using Neural Networks
0120 Local Point Matching Network for Stabilized Crowd Counting and Localization
0124 Boundary-Aware Polyp Segmentation Network
0127 Semi-Supervised Distillation Learning Based on Swin Transformer for MRI Reconstruction
0128 Style-based Attentive Network for Real-World Face Hallucination
0129 Discriminative Distillation to Reduce Class Confusion in Continual Learning
0132 Driver Behavior Decision Making based on Multi-Action Deep Q Network in Dynamic Traffic Scenes
0135 Capturing Prior Knowledge in Soft Labels for Classification with Limited or Imbalanced Data
0146 Triplet Ratio Loss for Robust Person Re-identification
0147 Two-stage Object Tracking Based on Similarity Measurement for Fused Features of Positive and Negative Samples
0149 Semi- and self-supervised model for scene text recognition with few labels
0152 Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification
0158 Locally Geometry-Aware Improvements of LOP for Efficient Skeleton Extraction
0159 Manifold-Driven and Feature Replay Lifelong Representation Learning on Person ReID
0161 WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation
0163 Infrared Object Detection Algorithm Based on Spatial Feature Enhancement
0165 Multi-source information-shared domain adaptation for EEG emotion recognition
0166 Caged Monkey Dataset: A New Benchmark for Caged Monkey Pose Estimation
0167 Multi-Level Temporal Relation Graph for Continuous Sign Language Recognition
0171 SteelyGAN: Semantic Unsupervised Symbolic Music Genre Transfer
0172 SUDANet:A Siamese UNet with Dense Attention Mechanism for Remote Sensing Image Change Detection
0175 Dual-rank attention module for fine-grained vehicle model recognition
0177 Cascade Scale-aware Distillation Network for Lightweight Remote Sensing Image Super-Resolution
0178 TFA-track:Temporal Features Aggregration for UAV Tracking and A Unified Benchmark
0179 Coupled Learning for Kernel Representation and Graph Tensor in Multi-view Subspace Clustering
0182 Automatic glottis segmentation method based on lightweight U-net
0185 Decouple U-Net: A Method for the Segmentation and Counting of Macrophages in Whole Slide Imaging
0186 A Local-Global Self-attention Interaction Network for RGB-D Cross-modal Person Re-identification
0187 Object Detection Based on Embedding Internal and External Knowledge
0194 Enhancing Transferability of Adversarial Examples with Spatial Momentum
0196 FOV Recognizer: Telling the Field of View of Movie Shots
0197 A Zero-training Method for RSVP-based Brain Computer Interface
0201 Spherical Transformer: Adapting Spherical Signal to Convolutional Networks
0202 ComLoss: A Novel Loss towards More Compact Predictions for Pedestrian Detection
0203 Mining Diverse Clues with Transformers for Person Re-identification
0205 Waterfall-Net: Waterfall Feature Aggregation for Point Cloud Semantic Segmentation
0209 AIA: Attention in Attention  within Collaborate Domains
0212 Correlated Matching and Structure Learning for Unsupervised Domain Adaptation
0213 An improved tensor network for image classification in histopathology
0214 Gradient-Rebalanced Uncertainty Minimization for Cross-Site Adaptation of Medical Image Segmentation
0221 Remote sensing image detection based on attention mechanism and YOLOv5
0228 Spatial-Channel Mixed Attention based Network for Remote Heart Rate Estimation
0230 Rider Re-identification Based on Pyramid Attention
0236 Detection of Pin Defects in Transmission Lines Based  on Dynamic Receptive Field
0240 Few-Shot Object Detection Based On Latent Knowledge Representation
0242 Federated Twin Support Vector Machine
0245 Self-Supervised Learning for Sketch-Based 3D Shape Retrieval
0251 Sparse LiDAR and Binocular Stereo Fusion Network for 3D Object Detection
0254 Beyond Vision: A Semantic Reasoning Enhanced Model for Gesture Recognition with Improved Spatiotemporal Capacity
0255 DeepEnReg: Joint Enhancement and Affine Registration for Low-contrast Medical Images
0260 SemanticGAN: Facial Image Editing with Semantic to Realize Consistency
0261 Infrared and Near-Infrared Image Generation via Content Consistency and Style Adversarial Learning
0262 Adversarial VAE with Normalizing Flows for Multi-Dimensional Classification
0268 Fluorescence Microscopy Images Segmentation based on Prototypical Networks with a few Annotations
0270 TMCR: A Twin Matching Networks for Chinese Scene Text Retrieval
0273 Fuzzy Twin Bounded Large Margin Distribution Machines
0280 PolyTracker: Progressive Contour Regression for Multiple Object Tracking and Segmentation
0281 Identification of bird s nest hazard level of transmission line based on improved yolov5 and location constraints
0283 Mutual Learning Inspired Prediction Network for Video Anomaly Detection
0286 Adaptive Open Set Recognition with Multi-Modal Joint Metric Learning
0288 A RAW Burst Super-Resolution Method with Enhanced Denoising
0289 Harnessing Multi-Semantic Hypergraph for Few-Shot Learning
0290 Few-Shot Segmentation via  Rich Prototype Generation and  Recurrent Prediction Enhancement
0291 SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image
0292 Full Head Performance Capture Using Multi-Scale Mesh Propagation
0297 Feature Difference Enhancement Fusion for Remote Sensing Image Change Detection
0298 Weakly Supervised Video Anomaly Detection with Temporal and Abnormal Information
0300 Weighted Graph Based Feature Representation for Finger-Vein Recognition
0303 Cascade Multiscale Swin-Conv Network for Fast MRI Reconstruction
0307 Learning Cross-domain Features for Domain Generalization on Point Clouds
0308 DEST: Deep Enhanced Swin Transformer toward Better Scoring for NAFLD
0309 Unpaired and Self-supervised Optical Coherence Tomography Angiography Super-resolution
0315 Dual-branch Memory Network for Visual Object Tracking
0316 Multi-Feature Fusion Network for Single Image Dehazing
0317 Prior-Guided Multi-scale Fusion Transformer for Face Attribute Recognition
0318 Combating Noisy Labels via Contrastive Learning with Challenging Pairs
0319 Instance-wise contrastive learning for multi-object tracking
0320 Image Magnification Network for Vessel Segmentation in OCTA Images
0321 Least-squares Estimation of Keypoint Coordinate for Human Pose Estimation
0323 Unsupervised Pre-training for 3D Object Detection with Transformer
0326 Multi-Grained Cascade Interaction Network for Temporal Activity Localization via Language
0327 CFA-Net: Cross-level Feature Fusion and Aggregation Network for Salient Object Detection
0328 Towards Class Interpretable Vision Transformer with Multi-Class-Tokens
0330 Group Activity Representation Learning with Self-Supervised Predictive Coding
0331 LAGAN: Landmark Aided Text to Face Sketch Generation
0336 Semantic Center Guided Windows Attention Fusion Framework for Food Recognition
0338 PilotAttnNet: Multi-Modal Attention Network for End-to-End Steering Control
0345 Disentangled Feature Learning for Semi-supervised Person Re-identification
0346 KITPose: Keypoint-Interactive Transformer for Animal Pose Estimation
0349 Skeleton-Based Action Quality Assessment via Partially Connected LSTM with Triplet Losses
0350 Adversarial Bidirectional Feature Generation for Generalized Zero-Shot Learning under Unreliable Semantics
0351 Detection Beyond What and Where: A Benchmark for Detecting Occlusion State
0354 Weakly Supervised Object Localization with Noisy-Label Learning
0355 Multimodal Violent Video Recognition based on  Mutual Distillation
0356 Exploiting Robust Memory Features for Unsupervised Reidentification
0357 CTCNet: A Bi-directional Cascaded Segmentation  Network Combining Transformers with CNNs  for Skin Lesions
0360 Finding Beautiful and Happy Images for Mental Health and Well-being Applications
0361 DMF-CL: Dense Multi-scale Feature Contrastive Learning for Semantic segmentation of Remote-sensing images
0366 MR Image Denoising Based On Improved Multipath Matching Pursuit Algorithm
0367 Stochastic Navigation Command Matching for Imitation Learning of a Driving Policy
0369 Self-Supervised Face Anti-Spoofing via Anti-Contrastive Learning
0372 Thai Scene Text Recognition with Character Combination
0373 Few-Shot Object Detection via Understanding Convolution and Attention
0375 Statistical characteristics of 3-D PET imaging: a comparison between conventional and total-body PET scanners
0376 TIR: A Two-stage Incest Recognition method for convolutional neural network
0379 Automatic Examination Paper Scores Calculation and Grades Analysis Based on OpenCV
0380 WAFormer Ship Detection in SAR Images Based on Window-aware Swin-Transformer
0384 Counterfactual Image Enhancement for Explanation of Face Swap Deepfakes
0394 Efficient License Plate Recognition via Parallel Position-aware Attention
0397 Enhanced Spatial Awareness For Deep Interactive Image Segmentation
0399 Every Corporation Owns Its Structure: Corporate Credit Ratings via Graph Neural Networks
0400 Image derain method for generative adversarial network  based on wavelet high frequency feature fusion
0403 Attributes based Visible-Infrared Person Re-identification
0404 Unsupervised Image Translation with GAN Prior
0407 Anchor-Free Location Refinement Network for Small License Plate Detection
0411 Unsupervised medical image registration based on multi-scale cascade network
0419 Multi-View LiDAR Guided Monocular 3D Object Detection
0421 GPU-Accelerated Infrared Patch-Image Model for Small Target Detection
0424 A Novel Local-global Spatial Attention Network for Cortical Cataract Classification in AS-OCT
0425 Dual Attention-guided Network for Anchor-free Apple Instance Segmentation in Complex Environments
0430 Part-based Multi-Scale Attention Network for Text-based Person Search
0433 Query-UAP: Query-efficient Universal Adversarial Perturbation for Large-scale Person Re-Identification Attack
0441 Robust Person Re-identification with Adversarial Examples Detection and Perturbation Extraction
0443 Hyperspectral and Multispectral Image Fusion Based on Unsupervised Feature Mixing and Reconstruction Network
0444 Information Adversarial Disentanglement for Face Swapping
0447 Hierarchical Long-Short Transformer for Group Activity Recognition
0448 Global Patch Cross-Attention for Point Cloud Analysis
0449 An adaptive PCA-like asynchronously deep reservoir computing for modeling data-driven soft sensors
0454 A Real-Time Polyp Detection Framework for Colonoscopy Video
0459 Dunhuang Mural Line Drawing Based on Bi-Dexined Network and Adaptive Weight Learning
0460 Discerning Coteaching: A Deep Framework for Automatic Identification of Noise Labels
0462 PRGAN: A Progressive Refined GAN for Lesion Localization and Segmentation on High-Resolution Retinal fundus Photography
0463 Attention-Aware Feature Distillation for Object Detection in Decompressed Images
0464 Improving Pre-trained Masked Autoencoder with Locality Enhancement for Person Re-identification
0466 Semantic-Aware Non-Local Network for Handwritten Mathematical Expression Recognition
0468 Multi-modal Finger Feature Fusion Algorithms on Large-Scale Dataset
0471 Deliberate Multi-Attention Network for Image Captioning
0472 Cross-Stage Class-Specific Attention for Image Semantic Segmentation
0473 Temporal Correlation-Diversity Representations for Video-based Person Re-Identification
0474 A Dense Prediction ViT Network for Single Image Bokeh Rendering
0480 Partial Least Square Regression via Three-factor SVD-type Manifold Optimization for EEG Decoding
0482 FIMF Score-CAM: Score-CAM Based Visual Explanations via Fast Integrating Multiple Features of Local Space for Deep Networks
0483 Double Recursive Sparse Self-Attention Based Crowd Counting In The Cluttered Background
0484 Multiscale Autoencoder with Structural-Functional Attention Network for Alzheimer's Disease Prediction
0485 Robust Liver Segmentation Using Boundary Preserving Dual Attention Network
0488 msFormer: Adaptive Multi-Modality 3D Transformer for Medical Image Segmentation
0489 Semi-supervised Medical Image Segmentation with Semantic Distance Distribution Consistency Learning
0494 CTFusion: Convolutions Integrate with Transformers for Multi-modal Image Fusion
0495 YFormer: a New Transformer Architecture for Video-query Based Video Moment Retrieval
0496 Learning Adaptive Progressive Representation for Group Re-identification
0500 Joint Pixel-level and Feature-level Unsupervised Domain Adaptation for Surveillance Face Recognition
0501 EllipseIoU: A General Metric for Aerial Object Detection
0503 EEP-Net: Enhancing local neighborhood features and Efficient semantic segmentation of scale Point Clouds
0505 Math Word Problem Generation with Memory Retrieval
0507 MultiGAN: multi-domain image translation from OCT to OCTA
0509 CARR-Net: Leveraging on Subtle Variance of Neighbors for Point Cloud Semantic Segmentation
0515 TransPND: A Transformer based Pulmonary Nodule Diagnosis Method on CT Image
0517 WTB-LLL: A Watercraft Tracking Benchmark Derived by Low-light-level Camera
0520 A Radar HRRP Target Recognition Method Based on Conditional Wasserstein VAEGAN and 1-D CNN
0523 Information Lossless Multi-Modal Image Generation for RGB-T Tracking
0524 Bayesian Neural Networks with Covariate Shift Correction for Classification in $gamma$-ray Astrophysics
0525 Dualray: Dual-view X-ray Security Inspection Benchmark and fusion detection framework
0526 Multi-scale Coarse-to-fine Network for Demoiréing
0529 Hightlight Video Detection in Figure Skating
0530 Adversarial Learning Based Structural Brain-network Generative Model for Analyzing Mild Cognitive Impairment
0532 3D Meteorological Radar Data Visualization with Point Cloud Completion  and Poisson Surface Reconstruction
0536 A 2.5D Coarse-to-fine Framework for 3D Cardiac CT View Planning
0538 Self-Supervised and Template-Enhanced Unknown-Defect Detection
0539 Heterogeneous Graph-based Finger Trimodal Fusion
0541 JFT: A Robust Visual Tracker Based On Jitter Factor and Global Registration
0542 MINIPI : a MultI-scale Neural network based impulse radio ultra-wideband radar Indoor Personnel Identification method
0546 Defect Detection for High Voltage Transmission Lines Based on Deep Learning
0549 Hand segmentation based on PAU-Net with complex backgrounds
0550 ORION: Orientation-Sensitive Object Detection
0553 General High-Pass Convolution: A Novel Convolutional Layer for Image Manipulation Detection
0557 Preference-aware Modality Representation and Fusion  for Micro-video Recommendation
0560 Weakly Supervised Semantic Segmentation of Echocardiography Videos via Multi-level Features Selection
0561 Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection
0567 Multi-Intent Compatible Transformer Network for Recommendation
0568 Background Suppressed and Motion Enhanced Network for Weakly Supervised Video Anomaly Detection
0572 An Infrared Moving Small Object Detection Method Based on Trajectory Growth
0573 BiTMulV: Bidirectional-Decoding based Transformer With Multi-View Visual Representation for Image Captioning
0576 DPformer: Dual-path transformers for geometric and appearance features reasoning in diabetic retinopathy grading
0577 Learning Contextual Embedding Deep Networks for Accurate and Efficient Image Deraining
0578 Traditional Mongolian Script Standard Compliance Testing Based on Deep Residual Network and Spatial Pyramid Pooling
0583 Deep Supervoxel Mapping Learning for Dense Correspondence of Cone-Beam Computed Tomography
0584 Single Deterministic Neural Network with Hierarchical Gaussian Mixture Model for Uncertainty Quantification
0587 JoinTW: A Joint Image-to-Image Translation and Watermarking Method
0592 Transmission tower detection algorithm based on feature-enhanced convolutional network in remote sensing image
0593 MobileNet V3 Large Lightweight Network-based Palmprint Recognition Algorithm
0594 VDSSA: Ventral & Dorsal Sequential Self-attention AutoEncoder for Cognitive-Consistency Disentanglement
0598 "Disentangled OCR: A More Granular Information for ""Text""-to-Image Retrieval"
0616 Human Knowledge-Guided and Task-Augmented Deep Learning for Glioma Grading
0617 Semantic-Augmented Local Decision Aggregation Network for Action Recognition
0618 Exploring Masked Image Modeling for Face Anti-Spoofing
0620 CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter
0621 Consensus-Guided Keyword Targeting for Video Captioning
0627 Attention-guided Multi-modal and Multi-scale fusion for Multispectral Pedestrian Detection
0634 GNN-based structural dynamics simulation for modular buildings
0635 XPNet: Cross-Domain Prototypical Network for Zero-Shot Sketch-Based Image Retrieval
0636 OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms
Official account