

Episode 03: Cinjon Resnick, NYU, on activity and scene understanding
Feb 1, 2021
Cinjon Resnick, an AI researcher and PhD candidate at NYU, formerly with Google Brain, dives into the critical importance of scene understanding for generalization in machine learning. He shares his unique journey, from attempting to teach a baby through language and games to a pivotal moment with circus arts that reshaped his focus towards activity recognition. Cinjon highlights the underrated MetaSIM papers, discusses the intricacies of motion recognition, and proposes intriguing new research directions that could redefine our approach to AI.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Intro
00:00 • 4min
Challenges in Activity Recognition and Learning
03:30 • 14min
Navigating Scene Understanding in Robotics
17:05 • 22min
Understanding Infant Cognition and Computational Techniques
38:42 • 2min
Exploring the Ridge Runner Method and Its Implications for Solution Diversity
40:26 • 5min
Revolutionizing Scene Understanding in AI
45:51 • 10min
Evolving Understanding of Research and Inquiry
55:54 • 4min