November 26, 2019, INRIA, C building, 4th floor, C434
2 Rue Simone IFF, 75012 Paris
09:00-09:30 |     | Breakfast: Espace Daumesnil, ground floor | ||
09:30-10:00 |   | Antoine Miech |   | Learning Visual Representations from Uncurated Instructional Videos |
10:00-10:30 |   | Bruno Korbar |   | Multimodal approach to video understanding |
10:30-10:45 |   | Makarand Tapaswi |   | Spatio-Temporal Modeling with Graph Neural Networks for Action Detection |
10:45-11:00 |   | Pierre Jacob |   | Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings |
11:00-11:15 |   | Hugo Germain |   | Sparse-to-Dense Matching for Long-Term Visual Localization |
11:15-11:30 |   | Xi Shen |   | Computer Vision, Historical and Artistic data |
11:30-12:00 |   | Taesung Park |   | GauGAN: Photorealistic Image Synthesis using SPADE |
12:00-14:00 |   | Lunch | ||
14:00-14:30 |   | Thibault Groueix |   | Learning surfaces |
14:30-15:00 |   | Yana Hasson |   | Joint Reconstruction of Hands and Objects |
15:00-15:30 |   | Allan Jabri |   | Learning Correspondence from the Cycle-consistency of Time |
15:30-15:40 |   | Break | ||
15:40-15:55 |   | Alexei Efros |   | Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity |
15:55-16:15 |   | Robin Strudel |   | Learning to combine primitive skills |
16:15-16:30 |   | Igor Kalevatykh |   | Learning to build 3D categories |
16:30-16:45 |   | Yann Labbe |   | Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning |
16:45-17:00 |   | Anna Kukleva |   | Learning Interactions and Relationships between Movie Characters |