SIVIC Josef

Computer Vision

josef.sivic [at] inria.fr

Josef Sivic

Short bio

Senior researcher (Directeur de recherche) at Inria, Distinguished researcher at Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague. Recipient of an ERC Starting Grant (2013), Sullivan Phd Thesis Prize (2007), and the CVPR (2017) and two ICCV (2017) test-of-time awards. Program chair of ICCV (2015) and associate editor of IJCV and TPAMI journals.

Topics of interest

Computer vision, machine learning, robotics

Project in Prairie

Josef Sivic will address weakly supervised learning and learning visual representations for reasoning, planning, and interacting with complex dynamic environments. He will collaborate with industry partners and contribute to teaching graduate level AI courses. His work will also involve the CIIRC institute in Prague, one of the international partners of PRAIRIE, where he has a part-time appointment.

Quote

Imagine, for example, an intelligent production line that automatically learns a new workflow by observing a skilled worker; or a rescue robot that autonomously completes tasks in an otherwise inaccessible environment. Another example is a house helper robot assisting disabled or elderly persons in unforeseen situations. All these applications require machines capable of understanding the changing visual world, learning new skills and adapting them to new environments and unforeseen situations. Building machines that have such capabilities is one of the central problems of artificial intelligence. In my research program, I would like to make a step towards solving these challenges.

SCHMID Cordelia

Computer Vision

cordelia.schmid [at] inria.fr / Twitter: @cordeliaschmid

Cordelia Schmid

Short bio

Cordelia Schmid is a research director at Inria Grenoble. Longuet- Higgins / Koenderink award for fundamental contributions in computer vision (2006, 2014, 2016, 2018). Fellow IEEE (2012). ERC advanced grant (2013). Humbolt research award (2015). Inria & French Academy of Science Grand Prix (2016). German National Academy of Sciences, Leopoldina (2017).

Topics of interest

Computer vision, machine learning, robotics

Project in Prairie

Machine perception has made significant progress over the past decade. There are now readily available models for tasks such as object detection, semantic segmentation and video classification. Our goal is to move towards high-level visual representations with an emphasis on autonomous learning for next generation AI systems.

Quote

Today’s systems are still surprisingly dependent on annotated data and the goal here is to design methods that learn independently without or with only sparse supervision and demonstrate evidence of autonomy Furthermore, learning should not be only static, but be based on the interaction with the world. We will pursue two main directions. The first one is on learning without or weak annotations given multi-modal data. The second one goes one step further and interacts with the world in order to learn without supervision, here without loss of generality based on a robot arm.

PONCE Jean

Computer Vision

jean.ponce [at] inria.fr

Jean Ponce

Short bio

Professor and former director, Department of Computer Science (on leave at Inria since Fall 2017), Ecole normale superieure. Distinguished Visiting Faculty, NYU (Fall 2017-). IEEE Fellow (2003). Recipient of an ERC Sr. Grant (2011) and the CVPR and ICML test-of-time awards (2016 and 2019). Sr. Editor-in-Chief, International Journal of Computer Vision (2019-).

Topics of interest

Computer vision, image processing, machine learning, robotics

Project in Prairie

Jean Ponce will address scale and supervision issues in vision, visually guided robotics, the NLP/vision interface, biological image restoration, cultural heritage preservation, and “blue-sky” collaborations with industry in vision and robotics. He will participate in the PSL AI graduate school, and develop a reference annual AI summer school.

Quote

Today’s computer vision technology is quite good at identifying animals, people, or natural and man-made objects in cluttered images and videos. But it relies on a humongous amount of manual annotation to learn the corresponding visual models. The vision systems of tomorrow will have to continuously learn from data with a much weaker level of human supervision, to adapt to new users for digital assistants or new routes and driving conditions for autonomous cars, and truly leverage the billions of images available on the Internet. This change of paradigm is necessary for the successful large-scale deployment of computer vision technology, and it is a central scientific challenge for our field.

LAPTEV Ivan

Computer Vision

ivan.laptev [at] inria.fr

Ivan Laptev

Short bio

Senior researcher at INRIA Paris and head of scientific board at VisionLabs, holds PhD degree from the Royal Institute of Technology (2004) and HDR degree from Ecole Normale Superieure (2013). Recipient of an ERC Starting Grant (2012) and an ICCV Helmholtz prize (2017). Program chair for CVPR (2018) and associate editor of IJCV and TPAMI journals.

Topics of interest

Computer vison, robotics, machine learning

Project in Prairie

Ivan Laptev will address the synergy between computer vision, robotics and natural language understanding. He will focus on learning embodied visio-linguistic representations for robotics exploring methods such as deep imitation, reinforcement learning and weakly-supervised learning for transferring knowledge from human demonstrations and instructions. He will collaborate with industrial partners and teach classes at the MVA Mater program.

Quote

Deep neural networks and machine learning have recently revolutionized computer vision. Typical proxy tasks such as object recognition and semantic image segmentation have achieved maturity. Yet, this progress so far had only limited influence on robotics. While perception and vision in particular are crucial components of robotics, traditional robotics methods typically decouple perception from control. With the advances in deep learning, an integrated approach of learning visual representations together with control functions now gives an opportunity for a breakthrough in the field. My goal in PRAIRIE is to bring advances of computer vision and natural language processing to robotics. While supervised learning has been crucial for the progress in computer vision, full supervision is rarely available for robotics tasks. Overcoming this limitation will be a major scientific challenge of the project.

COHEN Laurent

Image Analysis

cohen [at] ceremade.dauphine.fr

Laurent Cohen EPSON MFP image

Short bio

Research Director CNRS at Ceremade, Université Paris-Dauphine. Grand Prix from the French Academy of Sciences, EADS Foundation, 2009. IEEE Fellow for contributions to computer vision technology for medical imaging, 2010. For many years, he has been editorial member of the Journal of Mathematical Imaging and Vision, Medical Image Analysis and Machine Vision and Applications.

Topics of interest

Computer vison, image processing, Geodesics, Partial Differential Equations, Variational Methods, machine learning

Project in Prairie

Laurent Cohen’s research will focus on variational methods, PDEs and ML for image analysis, like object segmentation, shape analysis and deformation, in 2D or 3D images or point clouds. Applications lie in geometric structures present in biomedical imaging, in collaboration with institutes, hospitals or industry. He will participate in the PSL AI graduate school.

Quote

In the past 35 years, my research has focused on variational methods and Partial Differential Equations for Image Analysis with Deformable models and geodesic methods. A large part of my research has been done for image segmentation and shape recognition with applications in biomedical imaging, in collaboration with industry or hospitals (15 PhD supervision, among 25, with applications to biomedical imaging). Current work involves various aspects of Machine Learning.

Main topics:

Geodesic Methods: Image Segmentation, Active Contours Revisited. Applications to Medical Imaging.
Deformable Models: Edge-based or Region-based active contours, curve and surface Reconstruction, Image Segmentation and Restoration.
Machine Learning: Object segmentation and recognition.