Video and Language - Prof. Jiebo Luo, University of Rochester

Title: Video and Language Abstract: Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognitionof video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing vid eos using a predefined yet limited vocabulary. Thanks to the recent develo pment of deep learning techniques, researchers in vision and NLP communit ies are now striving to bridge videos with natural language in order to mo ve beyond classification to interpretation, which should be regarded as t he ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing te chniques, including video-language alignment, language localization in v ideos, video captioning, and video emotion analysis. Biography: Professor Jiebo Luo joined the University of Rochester in 2011 after a p rolific career of over fifteen years at Kodak Research Laboratories. He ha s been involved in numerous technical conferences, including serving as t he program co-chair of ACM Multimedia 2010, IEEE CVPR 2012, and IEEE ICI P 2017. He has served on the editorial boards of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on M ultimedia (TMM), IEEE Transactions on Circuits and Systems for Video Tech nology (TCSVT), IEEE Transactions on Big Data (TBD), ACM Transactions onIntelligent Systems and Technology (TIST), Pattern Recognition, Knowled ge and Information Systems (KAIS), Machine Vision and Applications, andJournal of Electronic Imaging. He is a Fellow of the ACM, AAAI, IEEE, IAPR and SPIE.