Deep Learning for Computer Vision Applications
Informazioni sull'evento
Informazioni sull'evento
Deep Learning for Computer Vision Applications
Lorenzo Baraldi is an Assistant Professor (RTD-A) at AImageLab. He works under the supervision of Prof. Rita Cucchiara on Deep Learning, video analysis and Multimedia. Among his research interests, he has worked on Egocentric Vision and Gesture Recognition, Temporal Video Segmentation and Retrieval, Saliency prediction, Video Captioning, Visual-Semantic alignment. In 2016, together with Prof. Rita Cucchiara, Prof. Costantino Grana and Dr. Simone Calderara, he has been author of the winning proposal for the Facebook AI Research Partnership, with which AImageLab has been selected as one of the 15 world-class research labs in Europe to receive a GPU-based server. In 2017 he worked in the FAIR (Facebook AI Research) lab in Paris, under the supervision of Hervé Jégou and Matthijs Douze. He develops and maintains Speaksee, a PyTorch that provides utilities for working with Visual-Semantic data, developed at AImageLab.
Guido Borghi is a post-doc at the University of Modena and Reggio Emilia. His research interests include Computer Vision and Deep Learning techniques applied to intensity and depth images. Among his research topics, he has worked on Driver Attention Monitoring, Gesture Analysis, Face Recognition and Body Pose Estimation. In 2018, he has spent four months at Stanford University at the Stanford Vision and Learning Lab working on Human-Robot Interaction. He is also a member of the RedVisionLab, working in collaboration with Ferrari S.p.A., and he is involved in research for Anomaly Detection with Italian Railway Company (RFI). He has served as a reviewer in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and ICCV 2017 and 2019.
Marcella Cornia is currently a third year PhD student at the International Doctorate School in ICT of the University of Modena and Reggio Emilia. She works under the supervision of Prof. Rita Cucchiara on deep learning, and computer vision. Her research interests include visual saliency prediction, image and video captioning, visual-semantic alignment, and multimedia for cultural heritage. In 2017, she won the LSUN Saliency Prediction Challenge, held in conjunction with the Scene Understanding Workshop at CVPR. In 2018, she received two travel grants to attend the Women in Computer Vision Workshop at CVPR and ECCV, which took place in Salt Lake City and Munich respectively.