Vincent Casser

Building the World's Most Experienced Driver.

Part of Aude Oliva's Computational Perception & Cognition lab (CSAIL). Developed novel algorithms and machine learning models to mimic human visual memory and human attention. As part of the Memento project, released the world's largest video memorability dataset (ECCV'20).

Google Brain Robotics: Worked on unsupervised learning of depth, object motion and egomotion from purely monocular video. Developed novel method introducing fusion, object motion handling and learnable size constraints, outperforming existing methods by a significant margin on all public benchmarks. First-authored patent and publication (AAAI'19).

Research Internship in the Image and Video Understanding Lab (IVUL) on autonomous navigation and deep learning from simulation at Visual Computing Center (VCC), King Abdullah University of Science and Technology (KAUST), Kingdom of Saudi Arabia.

Teaching assistant for software engineering classes on imperative and object-oriented programming. Field of work: mentoring students in tutorials, revising and grading student submissions, designing programming assignments.

Machine Learning, Data Analytics, Computer Vision, Software Development, Scientific Computing, Statistics

Computer Vision, Machine Learning, Software Development, Traditional AI, Computational Complexity