The Fourth Christmas Colloquium on Computer Vision
Wednesday, 26 December 2018, 14:00 — 19:30
The fourth edition of colloquium will see five eight researchers (some regular participants and some new) presenting their state-of-the-art work related to computer vision. Each talk will have an introductory part to make it accessible to a wider audience. Some minimal level of familiarity with modern computer vision is assumed. The talks will be in English.
NEW LOCATION: this year colloquium will move to Samsung AI Center at Lesnaya 5, 50 meters from Belorusskaya (Ring line). NB: Samsung has kindly provided the venue but is not the organizer of the meeting.
Attendance is free of charge, but registration is required, please fill in this form.
The registration is closed. The meeting is fully booked. It will be impossible to access colloquium if you have not been registered. Please do not come without registration, we will not be able to let you in!
SCHEDULE (tentative)
14:00 — 15:00 Nikolay Savinov (Google Brain, Zurich), “Episodic Memory for Sensorimotor Control”
15:00 — 15:20 Bogdan Bugaev (Higher School of Economics, Saint-Petersburg), “Combining 3D Model Contour Energy and Keypoints for Object Tracking”
15:20 — 15:40 Break
15:40 — 16:00 Alexander Vakhitov (Samsung AI Center and Skoltech, Moscow), “Improving Robustness and Accuracy of Point+Line Visual SLAM”
16:00 — 16:30 Eldar Insafutdinov (Max Planck Institute for Informatics, Saarbruecken), “Unsupervised Learning of 3D Object Shape and Camera Pose”
16:30 — 17:00 Natalia Neverova (Facebook AI Research, Paris), “DensePose++”
17:00 — 17:30 Break (+pizza)
17:30 — 18:00 Yaroslav Ganin (DeepMind, London), “Synthesizing Programs for Images using Reinforced Adversarial Learning”
18:00 — 19:00 Alexey Dosovitskiy (Intel Labs, Munich), “Learning to drive, fly, and walk”
19:00 — 19:30 Sergey Tulyakov (Snap Inc, California), “Learning representations for video generation, prediction and retargeting”
The meeting is supported by the Ministry of Education and Science grant RFMEFI61516X0003.
The 1st Colloquium webpage can be found here.
See you at the new place!
