TRANS-AM: Transfer Learning by Aggregating Dynamics Models for Soft Robotic Assembly
Precise Multi-Modal In-Hand Pose Estimation using Low-Precision Sensors for Robotic Assembly
Path Planning using Neural A* Search
Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data
Crowd Density Forecasting by Modeling Patch-based Dynamics
Decentralized Learning of Generative Adversarial Networks from Multi-Client Non-iid Data
Future Person Localization in First-Person Videos
Dynamic Object Scanning: Object-Based Elastic Timeline for Quickly Browsing First-Person Videos
Browsing Group First-Person Videos with 3D Visualization
Temporal Localization and Spatial Segmentation of Joint Attention in Multiple First-Person Videos
Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
Visual Motif Discovery via First-Person Vision
Discovering Objects of Joint Attention via First-Person Sensing
Ego-surfing first person videos
Predicting where we look from spatiotemporal gaps
Learning aspects of interest from Gaze
Single Image Segmentation with Estimated Depth
Gaze Probing: Event-Based Estimation of Objects Being Focused On