Lorenzo Seidenari

Latest

• Deep Variational Learning for 360 Adaptive Streaming
• FLODCAST: Flow and depth forecasting via multimodal recurrent architectures
• COMPUTER-IMPLEMENTED METHOD FOR PREDICTING MULTIPLE FUTURE TRAJECTORIES OF MOVING OBJECTS
• Explainable Sparse Attention for Memory-Based Trajectory Predictors
• Explaining autonomous driving with visual attention and end-to-end trainable region proposals
• SMEMO: social memory for trajectory forecasting
• Fast and effective AI approaches for video quality improvement
• Deep variational learning for multiple trajectory prediction of 360° head movements
• Online Deep Clustering with Video Track Consistency
• Vehicle Trajectories from Unlabeled Data through Iterative Plane Registration
• Language Based Image Quality Assessment
• LANBIQUE: LANguage-Based Blind Image QUality Evaluation
• Learning Group Activities from Skeletons without Individual Action Labels
• Multiple Future Prediction Leveraging Synthetic Trajectories
• MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction
• Am I Done? Predicting Action Progress in Videos
• Increasing Video Perceptual Quality with GANs and Semantic Coding
• Multiple Trajectory Prediction of Moving Agents with Memory Augmented Networks
• Deep Universal Generative Adversarial Compression Artifact Removal
• Fast Video Quality Enhancement Using GANs
• Towards Real-Time Image Enhancement GANs
• Vehicle Trajectories from Unlabeled Data through Iterative Plane Registration
• Object Recognition and Tracking for Smart Audio Guides
• Person Re-Identification from Depth Cameras using Skeleton and 3D Face Data
• Video Compression for Object Detection Algorithms
• Deep Artwork Detection and Retrieval for Automatic Context-Aware Audio Guides
• Automatic Image Annotation via Label Transfer in the Semantic Space
• Convex Polytope Ensembles for Spatio-Temporal Anomaly Detection
• Deep Generative Adversarial Compression Artifact Removal
• Indexing Quantized Ensembles of Exemplar-SVMs with Rejecting Taxonomies
• Outdoor Object Recognition for Smart Audio Guides
• PACE: Prediction-based Annotation for Crowded Environments
• Reading Text in the Wild from Compressed Images
• Spatio-temporal Closed-Loop Object Detection
• Understanding and localizing activities from correspondences of clustered trajectories
• Do Textual Descriptions Help Action Recognition?
• Indexing Ensembles of Exemplar-SVMs with Rejecting Taxonomies for Fast Evaluation
• Real-time Wearable Computer Vision System for Improved Museum Experience
• Fisher Encoded Convolutional Bag-of-Windows for Efficient Image Retrieval and Social Image Tagging
• MuseumVisitors: a dataset for pedestrian and group detection, gaze estimation and behavior understanding
• Real-Time Age Estimation from Face Imagery using Fisher Vectors
• Understanding Sport Activities from Correspondences of Clustered Trajectories
• WATSS: a Web Annotation Tool for Surveillance Scenarios
• A Cross-media Model for Automatic Image Annotation
• Adaptive Structured Pooling for Action Recognition
• Fisher vectors over random density forest for object recognition
• Local Pyramidal Descriptors for Image Recognition
• Real-time people counting from depth imagery of crowded environments
• Recognizing Actions from Depth Cameras as Weakly Aligned Multi-Part Bag-of-Poses
• L1-regularized Logistic Regression Stacking and CRF Smoothing for Action Recognition
• Real-time hand status recognition from RGB-D imagery
• Emergency Medicine Training with Gesture Driven Interactive 3D Simulations
• Effective Codebooks for Human Action Representation and Classification in Unconstrained Videos
• Multi-scale and real-time non-parametric approach for anomaly detection and localization
• Adaptive Video Compression for Video Surveillance Applications
• Space-time Zernike Moments and Pyramid Kernel Descriptors for Action Classification
• Event Detection and Recognition for Semantic Annotation of Video
• Dense Spatio-temporal Features For Non-parametric Anomaly Detection And Localization
• Non-parametric Anomaly Detection Exploiting Space-time Features
• Human Action Recognition and Localization using Spatio-temporal Descriptors and Tracking
• Recognizing Human Actions by Fusing Spatio-temporal Appearance and Motion Descriptors
• Effective Codebooks for Human Action Categorization