Michael S. Ryoo

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

2023

StARformer: Transformer With State-Action-Reward Representations for Robot Learning.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., November, 2023

Diffusion Illusions: Hiding Images in Plain Sight.

[BibT_eX]

[DOI]

CoRR, 2023

SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention.

[BibT_eX]

[DOI]

Isabel Leal

Krzysztof Choromanski

CoRR, 2023

Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities.

[BibT_eX]

[DOI]

CoRR, 2023

AAN: Attributes-Aware Network for Temporal Action Detection.

[BibT_eX]

[DOI]

CoRR, 2023

Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Active Reinforcement Learning under Limited Visual Observability.

[BibT_eX]

[DOI]

CoRR, 2023

VicTR: Video-conditioned Text Representations for Activity Recognition.

[BibT_eX]

[DOI]

CoRR, 2023

ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

RT-1: Robotics Transformer for Real-World Control at Scale.

[BibT_eX]

[DOI]

Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Active Vision Reinforcement Learning under Limited Visual Observability.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Language-based Action Concept Spaces Improve Video Self-Supervised Learning.

[BibT_eX]

[DOI]

Kanchana Ranasinghe

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the 18th International Conference on Machine Vision and Applications, 2023

SWAT: Spatial Structure Within and Among Tokens.

[BibT_eX]

[DOI]

Kumara Kahatapitiya

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Energy-Based Models for Cross-Modal Localization using Convolutional Transformers.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Open-vocabulary Queryable Scene Representations for Real World Planning.

[BibT_eX]

[DOI]

Keerthana Gopalakrishnan

Krzysztof Marcin Choromanski

Austin Stone

Daniel Kappler

Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.

[BibT_eX]

[DOI]

Andy Zeng

Maria Attarian

Brian Ichter

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Reducing Inference Latency with Concurrent Architectures for Image Recognition at Edge.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Edge Computing and Communications, 2023

Token Turing Machines.

[BibT_eX]

[DOI]

Keerthana Gopalakrishnan

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 2023

Attributes-Aware Network for Temporal Action Detection.

[BibT_eX]

[DOI]

Proceedings of the 34th British Machine Vision Conference 2023, 2023

Weakly-Guided Self-Supervised Pretraining for Temporal Activity Detection.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors.

[BibT_eX]

[DOI]

CoRR, 2022

Video + CLIP Baseline for Ego4D Long-term Action Anticipation.

[BibT_eX]

[DOI]

CoRR, 2022

Neural Neural Textures Make Sim2Real Consistent.

[BibT_eX]

[DOI]

CoRR, 2022

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.

[BibT_eX]

[DOI]

Andy Zeng

Adrian Wong

Stefan Welker

Krzysztof Choromanski

CoRR, 2022

Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space.

[BibT_eX]

[DOI]

Krzysztof Marcin Choromanski

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Hybrid Random Features.

[BibT_eX]

[DOI]

Valerii Likhosherstov

Dmitry Kalashnikov

Vikas Sindhwani

Adrian Weller

Proceedings of the Tenth International Conference on Learning Representations, 2022

StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Video Question Answering with Iterative Video-Text Co-tokenization.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Self-supervised Video Transformer.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

TRITON: Neural Neural Textures for Better Sim2Real.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 2022

2021

STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation.

[BibT_eX]

[DOI]

CoRR, 2021

Self-supervised Pretraining with Classification Labels for Temporal Activity Detection.

[BibT_eX]

[DOI]

CoRR, 2021

StARformer: Transformer with State-Action-Reward Representations.

[BibT_eX]

[DOI]

CoRR, 2021

TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?

[BibT_eX]

[DOI]

CoRR, 2021

Unsupervised Action Segmentation for Instructional Videos.

[BibT_eX]

[DOI]

CoRR, 2021

TokenLearner: Adaptive Space-Time Tokenization for Videos.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021

Visionary: Vision architecture discovery for robot learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2021

4D-Net for Learned Multi-Modal Alignment.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Recognizing Actions in Videos From Unseen Viewpoints.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Adaptive Intermediate Representations for Video Understanding.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

Coarse-Fine Networks for Temporal Activity Detection in Videos.

[BibT_eX]

[DOI]

Kumara Kahatapitiya

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Unsupervised Discovery of Actions in Instructional Videos.

[BibT_eX]

[DOI]

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020

Toward Collaborative Inferencing of Deep Neural Networks on Internet-of-Things Devices.

[BibT_eX]

[DOI]

IEEE Internet Things J., 2020

Correction to: Model-Based Robot Imitation with Future Image Similarity.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2020

Model-Based Robot Imitation with Future Image Similarity.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2020

Reducing Inference Latency with Concurrent Architectures for Image Recognition.

[BibT_eX]

[DOI]

CoRR, 2020

Edge-Tailored Perception: Fast Inferencing in-the-Edge with Efficient Model Distribution.

[BibT_eX]

[DOI]

CoRR, 2020

Learning Multimodal Representations for Unseen Activities.

[BibT_eX]

[DOI]

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

AViD Dataset: Anonymized Videos from Diverse Countries.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

AssembleNet++: Assembling Modality Representations via Attention Connections.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Adversarial Generative Grammars for Human Activity Prediction.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Password-Conditioned Anonymization and Deanonymization with Face Identity Transformers.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Evolving Losses for Unsupervised Video Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Differentiable Grammars for Videos.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Tiny Video Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Evolving Losses for Unlabeled Video Representation Learning.

[BibT_eX]

[DOI]

CoRR, 2019

Learning Differentiable Grammars for Continuous Data.

[BibT_eX]

[DOI]

CoRR, 2019

Collaborative Execution of Deep Neural Networks on Internet of Things Devices.

[BibT_eX]

[DOI]

CoRR, 2019

Learning Real-World Robot Policies by Dreaming.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019

Privacy-Preserving Robot Vision with Anonymized Faces by Extreme Low Resolution.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019

Temporal Gaussian Mixture Layer for Videos.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Evolving Space-Time Neural Architectures for Videos.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Robustly Executing DNNs in IoT Systems Using Coded Distributed Computing.

[BibT_eX]

[DOI]

Proceedings of the 56th Annual Design Automation Conference 2019, 2019

Early Detection of Injuries in MLB Pitchers From Video.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

Representation Flow for Action Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Model-based Behavioral Cloning with Future Image Similarity Learning.

[BibT_eX]

[DOI]

Proceedings of the 3rd Annual Conference on Robot Learning, 2019

2018

Distributed Perception by Collaborative Robots.

[BibT_eX]

[DOI]

IEEE Robotics Autom. Lett., 2018

Learning Shared Multimodal Embeddings with Unpaired Data.

[BibT_eX]

[DOI]

CoRR, 2018

Activity Detection with Latent Sub-event Hierarchy Learning.

[BibT_eX]

[DOI]

CoRR, 2018

Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices.

[BibT_eX]

[DOI]

CoRR, 2018

Joint Person Segmentation and Identification in Synchronized First- and Third-Person Videos.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2018, 2018

Learning to Anonymize Faces for Privacy Preserving Action Detection.

[BibT_eX]

[DOI]

Zhongzheng Ren

Yong Jae Lee

Proceedings of the Computer Vision - ECCV 2018, 2018

Forecasting Hands and Objects in Future Frames.

[BibT_eX]

[DOI]

Jangwon Lee

Proceedings of the Computer Vision - ECCV 2018 Workshops, 2018

Action-Conditioned Convolutional Future Regression Models for Robot Imitation Learning.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Fine-Grained Activity Recognition in Baseball Videos.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Learning Latent Super-Events to Detect Multiple Activities in Videos.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Real-Time Image Recognition Using Collaborative IoT Devices.

[BibT_eX]

[DOI]

Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning, 2018

Extreme Low Resolution Activity Recognition With Multi-Siamese Embedding Learning.

[BibT_eX]

[DOI]

Kiyoon Kim

Hyun Jong Yang

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017

Forecasting Hand and Object Locations in Future Frames.

[BibT_eX]

[DOI]

Jangwon Lee

CoRR, 2017

Learning robot activities from first-person human videos using convolutional future regression.

[BibT_eX]

[DOI]

Jangwon Lee

Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017

Multi-Type Activity Recognition from a Robot's Viewpoint.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Learning social affordance grammar from videos: Transferring human interactions to human-robot interactions.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

A holistic approach to interpreting human states in smart environments providing high quality of life.

[BibT_eX]

[DOI]

Proceedings of the Seventh International Conference on Emerging Security Technologies, 2017

Identifying First-Person Camera Wearers in Third-Person Videos.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Privacy-Preserving Human Activity Recognition from Extreme Low Resolution.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

Title Learning Latent Subevents in Activity Videos Using Temporal Attention Filters.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016

Multitype Activity Recognition in Robot-Centric Scenarios.

[BibT_eX]

[DOI]

IEEE Robotics Autom. Lett., 2016

First-Person Activity Recognition: Feature, Temporal Structure, and Prediction.

[BibT_eX]

[DOI]

Larry H. Matthies

Int. J. Comput. Vis., 2016

Privacy-Preserving Egocentric Activity Recognition from Extreme Low Resolution.

[BibT_eX]

[DOI]

Brandon Rothrock

Charles Fleming

CoRR, 2016

Temporal attention filters for human activity recognition in videos.

[BibT_eX]

[DOI]

CoRR, 2016

Learning Social Affordance for Human-Robot Interaction.

[BibT_eX]

[DOI]

Tianmin Shu

Song-Chun Zhu

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

2015

Building Unified Human Descriptors For Multi-Type Activity Recognition.

[BibT_eX]

[DOI]

Ilaria Gori

CoRR, 2015

Robot-centric Activity Recognition from First-Person RGB-D Videos.

[BibT_eX]

[DOI]

Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, 2015

Robot-Centric Activity Prediction from First-Person Videos: What Will They Do to Me'.

[BibT_eX]

[DOI]

Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction, 2015

Pooled motion features for first-person videos.

[BibT_eX]

[DOI]

Brandon Rothrock

Larry H. Matthies

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014

Early Recognition of Human Activities from First-Person Videos Using Onset Representations.

[BibT_eX]

[DOI]

CoRR, 2014

First-Person Animal Activity Recognition from Egocentric Videos.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Pattern Recognition, 2014

An Introduction to the 3rd Workshop on Egocentric (First-Person) Vision.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014

2013

Personal driving diary: Automated recognition of driving events from first-person videos.

[BibT_eX]

[DOI]

Comput. Vis. Image Underst., 2013

First-Person Activity Recognition: What Are They Doing to Me?

[BibT_eX]

[DOI]

Larry H. Matthies

Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

Recognizing Humans in Motion: Trajectory-based Aerial Video Analysis.

[BibT_eX]

[DOI]

Proceedings of the British Machine Vision Conference, 2013

2012

Toward a unified framework of motion understanding.

[BibT_eX]

[DOI]

Image Vis. Comput., 2012

Reliable object detection and segmentation using inpainting.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012

2011

Stochastic Representation and Recognition of High-Level Group Activities.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2011

Human activity analysis: A review.

[BibT_eX]

[DOI]

ACM Comput. Surv., 2011

One video is sufficient? Human activity recognition using active video composition.

[BibT_eX]

[DOI]

Wonpil Yu

Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV 2011), 2011

Personal driving diary: Constructing a video archive of everyday driving events.

[BibT_eX]

[DOI]

Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV 2011), 2011

Compensating for visually missing features: Scale adaptive recognition of objects using probabilistic voting.

[BibT_eX]

[DOI]

Ji Hoon Joung

Wonpil Yu

Proceedings of the 8th International Conference on Ubiquitous Robots and Ambient Intelligence, 2011

Background-aware pedestrian/vehicle detection system for driving environments.

[BibT_eX]

[DOI]

Proceedings of the 14th International IEEE Conference on Intelligent Transportation Systems, 2011

Interactive learning of human activities using active video composition.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Computer Vision Workshops, 2011

Human activity prediction: Early recognition of ongoing activities from streaming videos.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Computer Vision, 2011

2010

A task-driven intelligent workspace system to provide guidance feedback.

[BibT_eX]

[DOI]

Kristen Grauman

Comput. Vis. Image Underst., 2010

An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010.

[BibT_eX]

[DOI]

Chia-Chih Chen

Amit K. Roy-Chowdhury

Proceedings of the Recognizing Patterns in Signals, Speech, Images and Videos, 2010

Video scene analysis of interactions between humans and vehicles using event context.

[BibT_eX]

[DOI]

Jong Taek Lee

Proceedings of the 9th ACM International Conference on Image and Video Retrieval, 2010

2009

Real-Time Illegal Parking Detection in Outdoor Environments Using 1-D Transformation.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., 2009

Detection of object abandonment using temporal logic.

[BibT_eX]

[DOI]

Mach. Vis. Appl., 2009

Semantic Representation and Recognition of Continued and Recursive Human Activities.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2009

Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities.

[BibT_eX]

[DOI]

Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009

Stochastic representation and recognition of high-level group activities: Describing structural uncertainties in human activities.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009

2008

Human activities: Handling uncertainties using fuzzy time intervals.

[BibT_eX]

[DOI]

Proceedings of the 19th International Conference on Pattern Recognition (ICPR 2008), 2008

Observe-and-explain: A new approach for multiple hypotheses tracking of humans and objects.

[BibT_eX]

[DOI]

Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

2007

Robust Human-Computer Interaction System Guiding a User by Providing Feedback.

[BibT_eX]

[DOI]

Proceedings of the IJCAI 2007, 2007

Hierarchical Recognition of Human Activities Interacting with Objects.

[BibT_eX]

[DOI]

Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

Real-time detection of illegally parked vehicles using 1-D transformation.

[BibT_eX]

[DOI]

Proceedings of the Fourth IEEE International Conference on Advanced Video and Signal Based Surveillance, 2007

Detection of abandoned objects in crowded environments.

[BibT_eX]

[DOI]

Proceedings of the Fourth IEEE International Conference on Advanced Video and Signal Based Surveillance, 2007

2006

Semantic Understanding of Continued and Recursive Human Activities.

[BibT_eX]

[DOI]

Proceedings of the 18th International Conference on Pattern Recognition (ICPR 2006), 2006

Recognition of Composite Human Activities through Context-Free Grammar Based Representation.

[BibT_eX]

[DOI]

Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

2005

Evolving neural network ensembles for control problems.

[BibT_eX]

[DOI]

David Pardoe