A Robust Multi-Object Detection and Semantic Analysis Over Effective Deep Fused Networks for Scene Contextual Learning

Time-Distributed Deep Fusion Recognizer For Multi-Sensors Surveillance System

Deep Adaptive Locomotion Prediction Learning over Ontology Agents and Multi-sensory Devices

Human-Object Detection and Recognition

Computer Graphics, Human-computer Interaction, Parallel Computing, Computer Engineering

Multi-Vision Sensors based Human Interaction Recognition via Hierarchical Invariant Descriptors and Tree Hashing Graph Kernel

Multi-cue Fusion and Reweighted Genetic Algorithm for Physical Healthcare Routines on Wearable Accelerometer Sensors

Multi-Person Tracking and Crowd Behavior Detection via Particles Gradient Motion Descriptor and Improved Entropy Classifier

Deep Understanding of Human Anatomy: Multi-Vision Sensor-Based Body Parts Detection

Human Activity Recognition based on Deep Hybrid Learning Approach for UAV Surveillance

Context-Aware Learning for Deep Human Interaction Prediction over Multi-Sensory Videos

Multimodal IoT-based Deep Sensors Fusion for Human Motion Estimation and Posture Recognition

Deep Learning Algorithm over Multi Objects Detection and Recognition for Scene Classification

Deep Learning Estimations over Road Traffic Monitoring and Tracking

Intelligent Deep Traffic Surveillance and Multi-Vehicle Classification Over Complex Road Scenes

Deep Learning-based Leaf Classification and Disease Detection for Sustainable Plant Species Analysis

Unified Deep IoT System for Indoor Human Locomotion and Localization based on Smartphone Sensors

Locomotion Analytics Recognition over Smartphone Inertial and GPS Sensors

Enhanced Deep Learning Models for Aerial Visionary Sensors based Human Body Detection and Recognition

Deep Crowd Anomaly Recognition: Predicting Multi-Object Complex Scenes for Enhanced Safety and Surveillance

View Invariant Gesture Tracking and Recognition via 3D Hand Mask and Auto-Landmarks Localization

Automated Body Parts Estimation and Detection using Salient Maps and Gaussian Matrix Model

Robust Vital-Sign Monitoring of Human attention through deep Multi-Modal Sensor Fusion

A Smart Surveillance System for Pedestrian Tracking and Counting using Template Matching

Automatic 3D Posture Generation and Part Annotations for Deep Understanding of Human Interactions

Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier

Template Objects Detector and Feature Descriptors for Indoor / Outdoor Scenarios in RGB and Depth Images

Human Interactions over Spatio-Temporal and Geometrical Descriptors with Kernel Sliding Perceptron via Disparity Cameras

Pixel to 3D Voxel Reconstruction Using Octree-Based Network and Deep Learning