Research fields at AImageLab

Multimedia and Big Visual Data

Transformer-based Image Captioning Controllable Captioning Video Captioning with Naming Video matching and retrieval Scene detection in Broadcast Videos Deep Learning in videos Video Captioning Class Specific Segmentation Garment Selection and Color Classification Egocentric Video Summarization Face Recognition in News Streams

Videosurveillance and HBU

GAN4Surveillance: Generative Adversarial Networks for Attribute Classification Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World Duke Imagelab Multi-Target, Multi-Camera Tracking Project Spotting Prejudice Action and Gesture Recognition for Human Computer Interaction Group Detection and Crowd Analysis Multiple People Tracking People Re-identification ViSOR - Video Surveillance Online Repository People trajectory analysis and anomaly detection People Tracking From Multiple Cameras Video Action Detection Trajectory Prediction

Cultural Heritage and Digital Humanties

Visual-Semantic Domain Adaptation in Digital Humanities Art2Real: Translating Artworks to Photo-Realistic Images Layout and content analysis in Digitized Books Egocentric Video Registration and Architectural Details Retrieval EgoVision and Human Augmentation for Cultural Heritage

Embodied AI

Self-Supervised Navigation and Recounting Embodied Vision-and-Language Navigation Acquisition of 3D Environments for Robotic Navigation

Computer Vision and Pattern Recognition

Connected Components Labeling Visual Saliency Prediction Animal welfare analysis from 3D sensors 3D Computer Vision 3D Reconstruction of Skin Lesions for Tumor Diagnosis in OCT imaging Novelty Detection

Automotive

Video synthesis from Intensity and Event Frames Face Verification with Depth Images Hand Monitoring and Gesture Recognition for Human-Car Interaction Dr(eye)ve a Dataset for Attention-Based Tasks with Applications to Autonomous Driving Learning to Generate Faces from RGB and Depth data Mercury: a framework for Driver Monitoring and Human Car Interaction Landmark Localization in Depth Images Driver Attention through Head Localization and Pose Estimation Learning to Map Vehicles into Bird

New Visions: Sensors, Mobile, and Embedding

Egocentric Vision for Detecting Social Relationships Sensing floors Real Time Ellipse Detection on Mobile Devices Collaborative robot programming

Continual Learning

General Continual Learning