Students at PAISS
at
PAISS participants arrive at NAVER LABS Europe for the gala dinner.
Students with Florent Perronnin, Naila Murray and Diane Larlus.
Photo credit: Photos Gilles GALOYER – Studio JamaisVu !
The PAISS summer school was an undisputed success. The lectures were oustanding and the relaxed social events were ideal for networking. Speakers and students spent a lot of time together. The lectures will be available soon, more photos and a video of the gala. We’ll post here and on Twitter @naverlabseurope.
In the run up to the 1st PRAIRIE Artificial Intelligence Summer School ‘PAISS‘ we thought you might like to hear what they said!
Míriam Bellver
PhD in Computer Vision, Barcelona Supercomputing Center, Barcelona, Spain
I applied to PAISS because I thought it was a great opportunity to learn from top researchers in Artificial Intelligence.
I‘m very interested in the sessions on self-supervised learning, and weakly supervised and unsupervised methods for image and video interpretation, as I’m focusing my research on unsupervised and weakly supervised techniques for computer vision.
Viveka Kulharia
D.Phil. in Computer Vision, Dept of Engineering Science, Univ. Oxford, UK.
PAISS will help me interact with renowned researchers in computer vision and machine learning who will talk about the latest avenues in research in person. I’ll also get to meet students who are starting their PhD just like me. I’m actually interested in all the sessions to broaden my view but those most related to my field are Self-Supervised Learning, Weakly Supervised and Unsupervised Methods for Image and Video Interpretation, Machine Translation and Meta Learning. I think that the sessions will be very interactive and thus motivating.
Shasha Cui
Masters in Mathématique Vision Apprentissage (MVA), ENS Paris Saclay / ENSAE/ Polytechnique
I’m excited about PAISS since it’s really a great opportunity to meet these excellent researchers and learn something insightful from them in person. As well as the lectures I’m also interested in the practical sessions to gain more experience from industry. I think it might help me to figure out my research interest or work in the future.
Adeniyi Adeyemi
Ph.D. candidate Environmental science, University of South Africa (UNISA)
I expect wonderful interactive learning and the Practical Session will enable me to learn new models that can be implemented in my current research on satellite image analysis. All the sessions are important to me, especially Image Retrieval, Supervised and Unsupervised Methods for Image and Video Interpretation,Robotics for Vision, Machine Reading, Machine Translation, Reinforcement Learning and Meta Learning.
Rita Kuznetsova
Moscow Institute of Physics and Technology, Moscow, Russia
I applied to PAISS because of the topics of the lectures that strongly correlate with my research interests and duties and because the level of speakers is much higher than on average. I systematically read the papers of a number of them. I’m particularly interested in the poster session and the possibility to discuss research interests with colleagues and get their feedback.
Dmitry Petrov
Mathematical Biology (IITP Moscow) and Computer Science (UMass Amherst)
PAISS has an amazing selection of speakers and topics and I’m excited about all of them! However, topics which are particularly appealing to me are self-supervised learning, meta-learning and weakly supervised methods for image interpretation. I believe that these topics are very important for machine learning applications to neuro- and medical imaging problems data dimensionality is usually very high and large samples of annotated data are difficult or impossible to obtain (i.e. for rare neurodegenerative diseases). And of course I can’t wait for practical tutorials: they look really interesting! I expect to gain some preliminary knowledge of aforementioned areas, a lot of references to read, some hands-on experience from practical sessions and, most importantly, meet people who are passionate about artificial intelligence and its applications.
Lucas Fidon
CentraleSupelec and ENS Paris Saclay, France
I’ll be starting a PhD in October in machine learning for medical imaging applications so I’m particularly interested by this event and especially the oral presentations about self-supervised, unsupervised learning and reinforcement learning. I hope to learn from the best, grab new ideas, meet new people from the community and of course have fun!
Gurunath Reddy Madhumani
PhD Research Fellow (PhD in Music Signal Processing), Indian Institute of Technology Kharagpur India
I’m super excited to visit, meet and learn from INRIA and its partner AI researchers who are working on cutting edge AI technology. PAISS covers mostly all flavours of AI and its applications and I’m most interested in Self-supervised learning, Weakly supervised and Unsupervised learning and Reinforcement learning because ground truth creation and the manual tuning of the model to fit the given data is a very tedious and daunting task. These methods save lots of human effort, time and energy, and speed up the experimentation process to explore new ideas quickly.
Malik TIOMOKO A.
Masters in Mathématique Vision Apprentissage (MVA), ENS, Paris Saclay, France
A summer school is special because, in contrast to classical seminars, you have more time to digest the concepts presented and to discuss with people The practical sessions at PAISS are the most exciting for me because of the experience and discussions and that’s what I’ll keep in mind for a long time.
Overall, I expect to learn theoretical notions and practical skills and am particularly interested in the machine reading/machine translation lectures since my background is relatively light on these concepts.
Sergei Volodin
MSc in Computer Science, École Polytechnique Fédérale de Lausanne, Switzerland
I’m interested in theoretical aspects of Artificial Intelligence and would like to pursue a PhD in the area after I finish my MSc. To do so, I need to understand the main ideas in the field to choose a concrete topic where I could make a contribution during my PhD. I see PAISS as an excellent opportunity to experience different problems arising in Machine Learning by listening to experts in this field and by doing practical tasks. Moreover, I’d like to make connections with other researchers.
Matthias Müller
Ph.D. student, Image and Video Understanding Lab, Kaust, Thuwal, Saudi Arabia
PAISS features a great programme and an unbelievable list of speakers. It’s a unique opportunity to meet and interact with the giants in our field and build relationships with other students from around the globe. Great learning and networking opportunity while having a great time. I’m interested in the talk about robotics for vision. I believe that research at the intersection of robotics and machine learning¨ in particular vision¨ is essential to make AI more usable and impactful. I also think that the practical sessions will be interesting.
Nidham Gazagnadou
Engineering diploma in applied maths (specialization in optimization) / Master Mathématiques-Vision-Apprentissage (MVA), ENSTA ParisTech/ ENS Paris-Saclay
I wanted to have a first experience of a summer school in the field I’ll start my PhD in.
I’m mainly interested in the lectures related to optimization and reinforcement learning. I expect to learn a lot more about machine learning applications and exchange with researchers to get more insight about their work.
Amelia Jiménez Sánchez
PhD Researcher (Medical Image Analysis) at Pompeu Fabra University, Barcelona
I expect to get a deeper knowledge of the topics that I’m already familiar with at PAISS but also get some new ideas from different topics. It usually helps me to talk with people from other fields that have a different perspective of the problem that I’m currently working on. I’m particularly interested in the self-supervised, weakly supervised and unsupervised learning session because, in the medical community, it’s difficult to collect detailed annotated datasets. I’m also looking forward to the practical sessions to gain some hands-on experience.
More information on the AI summer school, co-organized by Inria and NAVER LABS Europe:
PAISS, PRAIRIE Artificial Intelligence Summer School, 2-6 July 2018
NAVER LABS joins PRAIRIE
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.