Ivan Laptev

email: <ivan.laptev at inria.fr>
phone: +33 (0) 1 80 49 44 21
address: INRIA,
              2 rue Simone IFF
              CS 42112
              75589 Paris Cedex 12
              Location on the map  

3 papers in CVPR'16, 2 papers in ECCV'16

Charades: Crowdsourced dataset for action recognition

Ivan Laptev is INRIA research director affiliated with INRIA Paris - Rocquencourt, a unit of the French National Institute for Research in Computer Science and Control. Ivan works in the WILLOW research group associated with École Normale Supérieure and led by Jean Ponce. He has obtained PhD degree from the Royal Institute of Technology (KTH) in 2004 where he was at the Computer Vision and Active Perception laboratory (CVAP).

Ivan's main research interests include visual recognition of human actions, objects and interactions. He has published over 50 papers at international conferences and journals of computer vision and machine learning. He serves as an associate editor of International Journal of Computer Vision and Image and Vision Computing Journal, he was/is an area chair for CVPR 2010, ICCV 2011, ECCV 2012, CVPR 2013 and ECCV 2014, he has co-organized several workshops and tutorials on human action recognition at major computer vision conferences. He has also co-organized a series of INRIA summer schools on computer vision and machine learning (2010-2013). Ivan was awarded ERC Starting Grant in 2012.







The goal of this work is to recognize realistic human actions in unconstrained videos such as in feature films, sitcoms, or news segments. Our contributions concern (i) automatic collection of realistic samples of human actions from movies based on movie scripts; (ii) automatic learning and recognition of complex action classes using space-time interest points and a multi-channel SVM classifier (iii) Improved results for human action recognition (we achieve 91.8%) on the public KTH actions dataset.



Learning, recognition and localization of human actions in realistic videos such as movies, TV news and home recordings. We focus on atomic actions such as "drinking", "smoking", "hand shaking" and demonstrate action detection in challenging realistic scenarios with substantial variation of actions in terms of subject appearance, motion, surrounding scenes, viewing angles and spatio-temporal extents.



Learning and efficient detection of object categories such as "horses", "bicycles", "motorcycles" and "cars". The method is based on discriminative learning of histogram support regions and demonstrates competitive performance on PASCAL VOC'05 and VOC'06 benchmarks.



Detection and segmentation of periodic motion in complex scenes with non-stationary background and motion parallax. The method exploits periodicity as a cue and makes no strong assumptions about the background. 3D periodic motion is considered to overcome view variations of moving objects over time.



Recognition of classes of human actions such as "running", "walking" and "hand clapping". The method exploits local action representation in terms of space-time interest points and does not rely on motion segmentation. Results are provided for KTH action database and for other complex scenes.



Detection of local events in video with distinct properties in space-time. The positions and the spatio-temporal descriptors of events are computed invariantly to scale and velocity transformations in video. Space-time interest points enable matching of corresponding space-time points across video sequences and may be used for video alignment and motion recognition.