Prof. Ivan Laptev is a visiting professor in the Computer Vision Department at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).

Prof. Laptev obtained his master's degree in computer science at the Royal Institute of Technology (KTH) in Sweden in 1997 and then worked as a research assistant at the Technical University of Munich. He obtained his Ph.D. in computer science from KTH in 2004 and went on to work as a postdoc with the INRIA Vista team in France. In 2005, he was appointed as an INRIA Research Scientist, and in 2013, he was named INRIA Research Director. Since 2009, he has worked at INRIA Paris, where from 2021 to 2023, he served as team leader for the WILLOW research project. He has authored over 150 technical articles, the most of which were published in prestigious peer-reviewed robotics, computer vision, and machine learning conferences as well as international journals. He has graduated 19 Ph.D. students who now pursue careers in industrial and academic research labs. Furthermore, he co-founded VisionLabs, a computer vision startup that now employs 250 people. As a program chair for CVPR 2018, ICCV 2023, and ACCV 2024, in addition to holding positions as associate editor of IJCV and TPAMI, Laptev has demonstrated a strong commitment to the scientific community. In addition, he will be the General Chair of ICCV 2029, which will bring the global computer vision community to the United Arab Emirates. Several lectures, workshops, and challenges at significant computer vision conferences have been co-organized by him. In addition, he co-organized the Machines Can See summits (2017–2023) and a number of INRIA summer schools in computer vision and machine learning (2010–2013). In 2012, he received an ERC Starting Grant, and in 2017, he was awarded the Helmholtz Prize for substantial impact in computer vision.

Prof. Laptev is most known for his work on action recognition in video. More generally, he is interested in learning visual and visuomotor representations for understanding, navigation and manipulation of dynamic scenes. In particular, his research has explored large-scale learning using language in the form of video scripts and narrations as a source of readily available, but noisy supervision. He has addressed a range of problems in visual recognition including image and video classification and retrieval, video question answering, video captioning as well 3D reconstruction of human bodies, hands and manipulated objects. More recently, he has explored the convergence of computer vision, natural language processing and robotics, addressing the problems of vision-language navigation and vision-language manipulation.