ETRI-Knowledge Sharing Plaform

State-Of-The-Art Deep Neural Network(DNN) Benchmark Datasets Estimation Method Moving Object Detection Deep Networks Competitive Performance Target Object Convolutional Networks Multi-Task Learning Network-Based Temporal Modeling Target And Background Conventional Methods Surveillance Camera Supervised Method Semi-Supervised Learning(SSL) Modeling Method Spatial And Temporal Human Pose Estimation Deep Reinforcement Learning Behavior Recognition Bounding Box Online Adaptation Partially Labeled Data Human Joints Face Image Person Detection Action Recognition Novel Method Short-Range Obstacle Avoidance Temporal Boundary Task-Based Resource-Efficient Backbone Network Consensus Model Deep Features Feature Alignment Face Alignment Graphics Processing Ground Truth Interaction Detection Memory Model Multiple Domains Sub-Models Segmentation Method Surgical Robot Video Object Segmentation Video Dataset Video Segment Need For Test Data Training Examples Training Sequence(TS) Two-Step Receptive Field Behavior Understanding Convolution Neural Network(CNN) Computation Time Effective Model Face Feature Extraction Graphic Processing Unit(GPU) Gaussian Model Gating Mechanism Highly Sensitive High Performance Model Parameter Model Misspecification Stacked Generalization Video Analytics Position Information Pre-Training Visual Tracker Video Sequences 3d Architectures Situation-Aware Object Position Testing Phase Joint Estimation Real-World Applications Appearance Modeling Context Modeling Efficiency And Effectiveness False Positive Fine Model Hyper-Parameters Joint Position Joint Coordinates Incomplete Data Modeling Architecture Detection Performance Contextual Information Semantic Word Embedding Log-Likelihood On-The-Fly Object-Related Recognition Method Adaptive Network Control Actions Critical Object Everyday Life Fine-Tuning Face Features Graph-Guided Keypoint Detection Learning Scenarios Multiple Datasets The Body Spatio-Temporal Features Safety-Critical Systems Prior Knowledge Video Classification Vision Sensor New Method Occlusion Processing Task-Specific Training And Testing Relation Model Real-World Data Anchor-Free Autonomous Driving Context-Aware Feature Deep Learning Models Delta Distribution Dynamic Background Existing State Future Development Feature Extracted Group Sparsity Human Posture Its Efficiency Long-Range Moving Camera Videos Pattern Recognition Positional Information Video Images Visual Surveillance System Video Surveillance Video Based Well-Aligned Self-Supervised Learning Tracking Accuracy Temporal Aggregation Real-Time Monitoring System Accuracy Improvement Background Subtraction Algorithm Bi-Modal Cctv Camera Camera Motion Computational Efficiency Collecting Data Computational Cost Detection Method Gaussian Distribution Graph Networks Image Classification Learning Approach Robust Performance Shape Prior Shape Estimation Social Issues State Estimation(SE) Motion Features Human-Object Interaction Ptz Camera Proposed Model Perspective Effect Uncertainty Estimation New Object Detection Object Region Object Properties Average Precision Appearance Features Background Modeling Computer Vision(CV) Dirac Delta Decision Networks Free Object Face Recognition Formula Presented Ground Vehicles Recognize People Pan-Tilt-Zoom Unmanned Aerial Vehicle Visual Sensing Word-To-Word Novel Algorithm Online Algorithm Standard Deviation(STD) Anchor-Based Attribute Recognition Classification Performance Catastrophic Forgetting Center Point Detection Algorithm Efficient Architecture End To End(E2E) Estimation Error Feature Hierarchy Generalization Performance Heterogeneous Object(HO) Human Action Surveillance Video Sensor Noise Parallel Processing Posture Prediction Visual Tracking Visual Object Tracking