INRIA’s Ivan Laptev presents “Weakly Supervised Learning from Images and Video” as part of the IRIM Robotics Seminar Series. The event will be held in the Marcus Nanotechnology Building, Rooms 1116-1118 from 12-1 p.m. and is open to the public.
Recent progress in visual recognition goes hand-in-hand with the supervised learning and large-scale training data. While the number of existing images and videos is huge, their detailed annotation is expensive and often ambiguous. In this talk we will discuss addressing these problems, focusing on weakly supervised learning methods using incomplete and noisy supervision for training. In the first part, I will discuss recognition from still images and will describe our work on weakly supervised convolutional networks for recognizing and localizing objects and human actions. The second part of the talk will focus on the learning of human actions from videos. In particular, we will consider understanding specific tasks from YouTube instruction videos and corresponding narrations. We will conclude with future challenges in and opportunities for visual recognition.
Ivan Laptev is a research director at INRIA Paris, France. He received a Habilitation degree from École Normale Supérieure in 2013 and a Ph.D. degree in Computer Science from the Royal Institute of Technology in 2004. Laptev’s main research interests include visual recognition of human actions, objects, and interactions. He received the ERC Starting Grant in 2012 and has published more than 50 papers at international conferences and in computer vision and machine learning journals. Laptev serves as an associate editor of IJCV and TPAMI journals and will serve as a program chair for CVPR ’18. He has served as an area chair for many conferences, including CVPR ’10, ’13, ’15, ’16; ICCV ’11; ECCV ’12, ’14; and ACCV ’14, ’16. Additionally, he has co-organized several tutorials, workshops, and challenges at major computer vision conferences. Laptev has also co-organized a series of INRIA summer schools on computer vision and machine learning (2010-2013).