Ivan Laptev

Senior researcher (Directeur de Recherche)
WILLOW project team
INRIA Paris
DI ENS


Office: C416
Email: ivan.laptev -at- inria.fr
Address: 2 rue Simone IFF, 75012 Paris, France



Short Bio: Ivan's main research interests include visual recognition of human actions, objects and interactions. He has published over 60 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 IEEE Transactions on Pattern Analysis and Machine Intelligence, he will be a program chair for CVPR 2018, he served as an area chair for major vision conferences, he has co-organized several workshops and tutorials on human action recognition and a series of ENS/INRIA summer schools on computer vision and machine learning (2010-2013). He was awarded ERC Starting Grant in 2012.

Students     Publications     CV

News





Students




Publications

"Joint Discovery of Object States and Manipulation Actions" (2017),
J.-B. Alayrac, J. Sivic, I. Laptev and S. Lacoste-Julien.; in Proc. ICCV'17, Venice, Italy.
Project page


"Weakly-Supervised Learning of Visual Relations" (2017),
J. Peyre, J. Sivic, I. Laptev and C. Schmid; in Proc. ICCV'17, Venice, Italy.
Project page


"Learning From Video and Text via Large-Scale Discriminative Clustering" (2017),
A. Miech, J.-B. Alayrac, P. Bojanowski, I. Laptev and J. Sivic; in Proc. ICCV'17, Venice, Italy.
Project page


"Learning from Synthetic Humans" (2017),
G. Varol, J. Romero, X. Martin, N. Mahmood, M.J. Black, I. Laptev and C. Schmid; in Proc. CVPR'17, Honolulu, Hawaii.
Project page


"Learnable pooling with Context Gating for video classification" (2017),
A. Miech, I. Laptev and J. Sivic; arXiv preprint arXiv:1706.06905.
Code


"Long-term Temporal Convolutions for Action Recognition" (2017),
G. Varol, I. Laptev and C. Schmid; in IEEE Trans. on Pattern Analysis and Machine Intelligence 2017.
Project page


"The THUMOS Challenge on Action Recognition for Videos "in the Wild"" (2017),
H. Idrees, A.R. Zamir, Y.-G. Jiang, A. Gorban, I. Laptev, R. Sukthankar and M. Shah; in Computer Vision and Image Understanding, 155, pp.1-23.
Thumos Challenge


"ContextLocNet: Context-aware deep network models for weakly supervised localization" (2016),
V. Kantorov, M. Oquab, M. Cho and I. Laptev; in Proc. ECCV'16, Amsterdam, The Netherlands.
Project page


"Hollywood in homes: Crowdsourcing data collection for activity understanding" (2016),
G. Sigurdsson, G. Varol, X. Wang, A. Farhadi, I. Laptev and A. Gupta; in Proc. ECCV'16, Amsterdam, The Netherlands.
Project page


"Much ado about time: Exhaustive annotation of temporal data" (2016),
G. Sigurdsson, O. Russakovsky, A. Farhadi, I. Laptev and A. Gupta; in Proc. HCOMP'16, Austin, TX, USA.
Project page


"Unsupervised learning from narrated instruction videos" (2016),
J.-B. Alayrac, P. Bojanowski, N. Agrawal, J. Sivic, I. Laptev and S. Lacoste-Julien; in Proc. CVPR'16, Las Vegas, USA.
Project page
Extended version:
"Learning from Narrated Instruction Videos" (2017),
J.-B. Alayrac, P. Bojanowski, N. Agrawal, J. Sivic, I. Laptev and S. Lacoste-Julien; to appear in IEEE Trans. on Pattern Analysis and Machine Intelligence.


"Instance-level video segmentation from object tracks" (2016),
G. Seguin, P. Bojanowski, R. Lajugie and I. Laptev; in Proc. CVPR'16, Las Vegas, USA.
Project page


"Thin-slicing for pose: Learning to understand pose without explicit pose estimation" (2016),
S. Kwak, M. Cho, I. Laptev; in Proc. CVPR'16, Las Vegas, USA.


"P-CNN: Pose-based CNN Features for Action Recognition" (2015), Project page
G. Chéron, I. Laptev and C. Schmid; in Proc. ICCV'15, Santiago, Chile.

"Context-aware CNNs for person head detection" (2015), Project page
T.-H. Vu, A. Osokin and I. Laptev; in Proc. ICCV'15, Santiago, Chile.

"Weakly-Supervised Alignment of Video With Text" (2015),
P. Bojanowski, R. Lajugie, E. Grave, F. Bach, I. Laptev, J. Ponce and C. Schmid; in Proc. ICCV'15, Santiago, Chile.

"Unsupervised Object Discovery and Tracking in Video Collections" (2015),
S. Kwak, M. Cho, I. Laptev, J. Ponce, and C. Schmid; in Proc. ICCV'15, Santiago, Chile.

"Is object localization for free? - Weakly-supervised learning with convolutional neural networks" (2015), Project page
M. Oquab, L. Bottou, I. Laptev and J. Sivic; in Proc. CVPR'15, Boston, Massachusetts, USA.

"On Pairwise Costs for Network Flow Multi-Object Tracking" (2015), Project page
V. Chari, S. Lacoste-Julien, I. Laptev and J. Sivic; in Proc. CVPR'15, Boston, Massachusetts, USA.

"Predicting Actions from Static Scenes" (2014), Project page
T.-H. Vu, C. Olsson, I. Laptev, A. Oliva and J. Sivic; in Proc. ECCV'14, Zurich, Switzerland.

"Weakly supervised action labeling in videos under ordering constraints" (2014), Project page
P. Bojanowski, R. Lajugie, F. Bach, I. Laptev, J. Ponce, C. Schmid and J. Sivic; in Proc. ECCV'14, Zurich, Switzerland.

"Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks" (2014), Project page
M. Oquab, L. Bottou, I. Laptev and J. Sivic; in Proc. CVPR'14, Columbus, Ohio, USA.
Earlier version: Technical Report HAL-00911179, Nov. 2013.

"Efficient feature extraction, encoding and classification for action recognition" (2014) Project page
V. Kantorov, I. Laptev in Proc. CVPR'14, Columbus, Ohio, USA.

"Finding Actors and Actions in Movies" (2013), Project page
P. Bojanowski, F. Bach, I. Laptev, J. Ponce, C. Schmid and J. Sivic; in Proc. ICCV'13, Sydney, Australia.

"Pose Estimation and Segmentation of People in 3D Movies" (2013), Project page
G. Seguin K. Alahari, J. Sivic and I. Laptev; in Proc. ICCV'13, Sydney, Australia.
Extended version:
"Pose Estimation and Segmentation of Multiple People in Stereoscopic Movies" (2015),
G. Seguin, K. Alahari, J. Sivic and I. Laptev; in IEEE Trans. on Pattern Analysis and Machine Intelligence, 37(8):1643-1655.

"Scene semantics from long-term observation of people" (2012), Project page
V. Delaitre, D.F. Fouhey, I. Laptev, J. Sivic, A. Gupta and A.A. Efros; in Proc. ECCV'12, Florence, Italy.

"People Watching: Human Actions as a Cue for Single-View Geometry" (2012), Project page
D.F. Fouhey, V. Delaitre, A. Gupta, A.A. Efros, I. Laptev and J. Sivic; in Proc. ECCV'12, Florence, Italy.
Extended version:
"People Watching: Human Actions as a Cue for Single View Geometry" (2014),
D. Fouhey, V. Delaitre, A. Gupta, A. Efros, I. Laptev and J. Sivic; in International Journal of Computer Vision, 110(3):259-274.

"Object Detection Using Strongly-Supervised Deformable Part Models" (2012), Project page
H. Azizpour and I. Laptev; in Proc. ECCV'12, Florence, Italy.

"Actlets: A novel local representation for human action recognition in video" (2012),
M.M. Ullah and I. Laptev; in Proc. ICIP'12, Orlando, Florida, USA.

"Learning person-object interactions for action recognition in still images" (2011)
V. Delaitre, J. Sivic and I. Laptev; in Proc. NIPS'11, Granada, Spain.

"Density-aware person detection and tracking in crowds" (2011), Video, Project page
M. Rodriguez, I. Laptev, J. Sivic and J.-Y. Audibert; in Proc. ICCV'11, Barcelona, Spain.

"Data-driven Crowd Analysis in Videos" (2011), Video, Project page
M. Rodriguez, J. Sivic, I. Laptev and J.-Y. Audibert; in Proc. ICCV'11, Barcelona, Spain.

"Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues" (2011), Project page
J. Lezama, K. Alahari, J. Sivic and I. Laptev; in Proc. CVPR'11, Colorado, US.

"Semi-supervised learning of facial attributes in video" (2010), Project page
N. Cherniavsky, I. Laptev, J. Sivic, and A. Zisserman in The First Int. Workshop on Parts and Attributes (in conjunction with ECCV 2010), Greece.

"Recognizing human actions in still images: a study of bag-of-features and part-based representations" (2010), Project page
V. Delaitre, I. Laptev end J. Sivic in Proc. BMVC'10, Aberystwyth, UK.

"Improving Bag-of-Features Action Recognition with Non-local Cues" (2010),
M.M. Ullah, S.N. Parizi and I. Laptev; in Proc. BMVC'10, Aberystwyth, UK.

"Automatic Annotation of Human Actions in Video" (2009),
O. Duchenne, I. Laptev, J. Sivic, F. Bach and J. Ponce; in Proc. ICCV'09, Kyoto, Japan.

"Evaluation of local spatio-temporal features for action recognition" (2009),
H. Wang, M. M. Ullah, A. Klaser, I. Laptev and C. Schmid; in Proc. BMVC'09, London, UK.

"Multi-View Synchronization of Human Actions and Dynamic Scenes" (2009),
E. Dexter, P. Perez and I. Laptev; in Proc. BMVC'09, London, UK.

"Actions in Context" (2009),
M. Marszałek, I. Laptev and C. Schmid; in Proc. CVPR'09, Miami, US.

"Modeling Image Context using Object Centered Grids" (2009),
S.N. Parizi, I. Laptev and A.T. Targhi; in Proc. DICTA'09, Melbourne, Australia.

"Cross-View Action Recognition from Temporal Self-Similarities" (2008),
I. Junejo, E. Dexter, I. Laptev and Patrick Perez; in Proc. ECCV'08, Marseille, France.
Extended version:
"View-Independent Action Recognition from Temporal Self-Similarities" (2010),
I. Junejo, E. Dexter, I. Laptev and P. Perez; in IEEE Trans. on Pattern Analysis and Machine Intelligence, 33(1):172-185.

"Learning realistic human actions from movies" (2008),
I. Laptev, M. Marszałek, C. Schmid and B. Rozenfeld; in Proc. CVPR'08, Anchorage, US.

"Retrieving actions in movies" (2007),
I. Laptev and P. Perez; in Proc. ICCV'07, Rio de Janeiro, Brazil.

"Video Copy Detection: a Comparative Study" (2007),
J. Law-To, L. Chen, A. Joly, I. Laptev, O. Buisson, V. Gouet-Brunet, N. Boujemaa and F.I. Stentiford; in Proc. CIVR'07, Amsterdam, The Netherlands, pp. 371-378.

"Improvements of Object Detection Using Boosted Histograms" (2006),
I. Laptev; in Proc. BMVC'06, Edinburgh, UK, pp. III:949-958.
Extended version:
"Improving Object Detection with Boosted Histograms" (2009),
I. Laptev; in Image and Vision Computing, vol. 27, issue 5, pp. 535-544.

"Periodic Motion Detection and Segmentation via Approximate Sequence Alignment" (2005),
I. Laptev, S.J. Belongie, P. Perez and J. Wills; in Proc. ICCV'05, Bijing, China, pp. I:816-823.

"Local Descriptors for Spatio-Temporal Recognition" (2004),
I. Laptev and T. Lindeberg; in ECCV Workshop "Spatial Coherence for Visual Motion Analysis", Springer LNCS Vol.3667, pp. 91-103.
Extended version:
"Local Velocity-Adapted Motion Events for Spatio-Temporal Recognition" (2007),
I. Laptev, B. Caputo, C. Schuldt and T. Lindeberg; in Computer Vision and Image Understanding, 108:207-229.

"Velocity adaptation of space-time interest points" (2004),
I. Laptev and T. Lindeberg; in Proc. ICPR'04, Cambridge, UK, pp.I:52-56.

"Galilean-diagonalized spatio-temporal interest operators" (2004),
T. Lindeberg, A. Akbarzadeh and I. Laptev; in Proc. ICPR'04, Cambridge, UK, pp.I:57-62.

"Recognizing Human Actions: A Local SVM Approach" (2004),
Christian Schuldt, Ivan Laptev and Barbara Caputo; in Proc. ICPR'04, Cambridge, UK, pp.III:32--36.

"Space-Time Interest Points" (2003),
I. Laptev and T. Lindeberg; in Proc. ICCV'03, Nice, France, pp.I:432-439.
Extended version:
"On Space-Time Interest Points" (2005),
I. Laptev; in International Journal of Computer Vision, vol 64, number 2/3, pp.107-123.

"Interest point detection and scale selection in space-time" (2003),
I. Laptev and T. Lindeberg; in Proc. Scale Space Methods in Computer Vision, Isle of Skye, UK, Springer LNCS vol.2695, pp.372-387.

"Velocity-adaptation of spatio-temporal receptive fields for direct recognition of activities: An experimental study" (2002),
I. Laptev and T. Lindeberg; in Proc. ECCV'02 Workshop on Statistical Methods in Video Processing, pp.61-66.
Extended version:
"Velocity-adaptation of spatio-temporal receptive fields for direct recognition of activities: An experimental study" (2004),
I. Laptev and T. Lindeberg; in Image and Vision Computing 22:105-116.

"Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering" (2002),
L. Bretzner, I. Laptev and T. Lindeberg; in Proc. 5th IEEE International Conference on Automatic Face and Gesture Recognition, Washington D.C., May, pp.423-428.

"Extraction of linear objects from interferometric SAR data" (2002),
O. Hellwich, I. Laptev and H. Mayer; in Int. J. Remote Sensing 23(3):461-475, 2002.

"A multi-scale feature likelihood map for direct evaluation of object hypotheses" (2001),
I. Laptev and T. Lindeberg; in Proc. IEEE Workshop on Scale-Space and Morphology, Vancouver, Canada, Springer LNCS vol.2106, pp.98-110.
Extended version:
"A distance measure and a feature likelihood map concept for scale-invariant model matching" (2003),
I. Laptev and T. Lindeberg; in International Journal of Computer Vision, vol 52, number 2/3, pp 97-120.

"Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features" (2001),
I. Laptev and T. Lindeberg; in Proc. IEEE Workshop on Scale-Space and Morphology, Vancouver, Canada, Springer LNCS vol.2106, pp.98-110.

"Agilo robocuppers: Robocup team description" (1999),
M. Klupsch, M. Luckenhaus, C. Zierl, I. Laptev, T. Bandlow, M. Grimme, K. Kellerer, and F. Schwarzer; in RoboCup-98: Robot Soccer World Cup II, Springer LNCS vol.1604, pp.446-451.

"Multi-Scale and Snakes for Automatic Road Extraction" (1998),
H. Mayer, I. Laptev, A. Baumgartner; in Proc. ECCV'98, Freiburg, Germany, Springer LNCS vol.1406, pp.720-733.
Extended version:
"Automatic extraction of roads from aerial images based on scale-space and snakes" (2000),
I. Laptev, H. Mayer, T. Lindeberg, W. Eckstein, C. Steger, and A. Baumgartner; in Machine Vision and Applications 12(1):23-31.

"Automatic Road Extraction Based on Multi-Scale Modelling, Context, and Snakes" (1997),
H. Mayer, I. Laptev, A. Baumgartner, C. Steger; in International Archives of Photogrammetry and Remote Sensing, (32) 3-2W3 , pp.106-113