Federico Becattini

Latest

• Defending from GeoLocalization through Adversarial Road Trips
• Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
• Attacking Attention of Foundation Models Disrupts Downstream Tasks
• 3D Pose Nowcasting: Forecast the future to improve the present
• Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
• Deep Variational Learning for 360 Adaptive Streaming
• Deepfake Detection by Exploiting Surface Anomalies: The SurFake Approach
• Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB
• FLODCAST: Flow and depth forecasting via multimodal recurrent architectures
• CrossFeat: Semantic Cross-modal Attention for Pedestrian Behavior Forecasting
• 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
• 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
• Multiple Future Prediction Leveraging Synthetic Trajectories
• MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction
• Am I Done? Predicting Action Progress in Videos
• Multiple Trajectory Prediction of Moving Agents with Memory Augmented Networks
• Vehicle Trajectories from Unlabeled Data through Iterative Plane Registration
• Indexing Quantized Ensembles of Exemplar-SVMs with Rejecting Taxonomies