ICCV Daily 2021 - Wednesday

Mathilde’s picks of the day (Wednesday): Mathilde Caron is currently finishing her PhD at Inria and Facebook AI Research (FAIR) in France. She has mainly been working on self-supervised representation learning for vision. Her supervisors are Julien Mairal at Inria and Piotr Bojanowski and Armand Joulin at Facebook . Before that, she graduated with a double master degree from École polytechnique in France and KTH Royal Institute of Technology in Sweden where she was mostly interested in applied mathematics and machine learning. Session 7 6269 Composable Augmentation Encoding for Video Representation … Session 8 7354 Swin Transformer: Hierarchical Vision Transformer Using Shifted … Session 8 3077 Self-Supervised Pretraining of 3D Features on Any Point-Cloud Session 8 10303 Efficient Visual Pretraining With Contrastive Detection Session 9 3906 Aligning Subtitles in Sign Language Videos For today, Wednesday 13 2 Mathilde’s Picks DAILY ICCV Wednesday Learn more about Mathilde’s work! Mathilde only forgot to recommend her own paper, today! She is presenting Emerging Properties in Self-Supervised Vision Transformers [session 8 7530]. You can view her pre-recorded presentation and PDF now and join her live Q&A session today (Wednesday) at 9:00-10:00 EDT. “The high-level goal of my research is to explore how we can build artificial intelligent visual systems able to understand the world. Indeed, it is appealing how easily humans and many animals can see the world and understand it effortlessly. They acquire such an understanding of the visual world autonomously, without the intervention of a supervisor explicitly telling them what, where or who is to be seen. This could suggest that visual perception can be achieved without too much explicit human supervision but simply by letting systems observe large amounts of visual inputs”