Sotabase

Career

· Researcher in Robotics and Computer Vision, UC Berkeley Department of Electrical Engineering and Computer Sciences2008–

Publications (185)

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Conference on Robot Learning · 2023
2,268
cited
RT-1: Robotics Transformer for Real-World Control at Scale
Robotics: Science and Systems · 2022
1,786
cited
Human activity analysis
ACM Computing Surveys · 2011
1,329
cited
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
International Conference on Learning Representations · 2022
687
cited
Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities
IEEE International Conference on Computer Vision · 2009
621
cited
Human activity prediction: Early recognition of ongoing activities from streaming videos
Vision · 2011
595
cited
First-Person Activity Recognition: What Are They Doing to Me?
2013 IEEE Conference on Computer Vision and Pattern Recognition · 2013
309
cited
Recognition of Composite Human Activities through Context-Free Grammar Based Representation
Computer Vision and Pattern Recognition · 2006
293
cited
Open-vocabulary Queryable Scene Representations for Real World Planning
IEEE International Conference on Robotics and Automation · 2022
238
cited
Learning to Anonymize Faces for Privacy Preserving Action Detection
European Conference on Computer Vision · 2018
216
cited
TokenLearner: Adaptive Space-Time Tokenization for Videos
Neural Information Processing Systems · 2021
206
cited
An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010
ICPR Contests · 2010
198
cited
Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
AAAI Conference on Artificial Intelligence · 2016
194
cited
Pooled motion features for first-person videos
Computer Vision and Pattern Recognition · 2014
185
cited
Semantic Representation and Recognition of Continued and Recursive Human Activities
International Journal of Computer Vision · 2009
177
cited
Representation Flow for Action Recognition
Computer Vision and Pattern Recognition · 2018
156
cited
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
arXiv.org · 2021
156
cited
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
arXiv.org · 2024
146
cited
Evolving Losses for Unsupervised Video Representation Learning
Computer Vision and Pattern Recognition · 2020
145
cited
Robot-Centric Activity Prediction from First-Person Videos: What Will They Do to Me?
IEEE/ACM International Conference on Human-Robot Interaction · 2015
135
cited
Sotabase
Michael S. Ryoo | Researcher Profile | Sotabase | Sotabase