← Authors

Michael S. Ryoo

38 papers · 2013–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (12) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (56) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ† Keyword Champion (6) 🧬 Topic Evolution 🀝 Dynamic Duo (14) πŸ‘₯ Mega-Team (55) πŸš€ Conference Pioneer πŸ’Ž Century Club (38) πŸ—ƒοΈ Keyword Collector (141) πŸ”₯ Unstoppable (9) πŸ“ˆ Trend Setter ❓ The Questioner ⚑ Prolific Year (5)

Conferences

CVPR (15) ECCV (8) CORL (3) ICCV (3) WACV (3) AAAI (2) NIPS (2) ICLR (1) IJCAI (1)

Top co-authors

AJ Piergiovanni (14) Anelia Angelova (10) Kumara Kahatapitiya (9) Xiang Li (3) Jinghuan Shang (3) Srijan Das (3) Yong Jae Lee (3) Kanchana Ranasinghe (3) Ted Xiao (2) David J. Crandall (2)

Research topics

Computer Vision (1)

Keywords

video understanding (8) activity recognition (6) self-supervised learning (5) representation learning (4) action recognition (4) video representation (3) temporal activity detection (3) convolutional neural network (3) contrastive learning (3) vision transformer (3) action detection (2) multi-scale feature (2) transfer learning (2) temporal structure (2) viewpoint invariance (2) multimodal learning (2) attention mechanism (2) model architecture (2) autoregressive model (2) robot action policy (2)

Papers

Adaptive Caching for Faster Video Generation with Diffusion Transformers ICCV 2025
Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders WACV 2024
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs CVPR 2024
Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities CVPR 2024
MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying CVPR 2024
VicTR: Video-conditioned Text Representations for Activity Recognition CVPR 2024
Grafting Vision Transformers WACV 2024
Language-based Action Concept Spaces Improve Video Self-Supervised Learning NIPS 2023
Weakly-Guided Self-Supervised Pretraining for Temporal Activity Detection AAAI 2023
Token Turing Machines CVPR 2023
SWAT: Spatial Structure Within and Among Tokens IJCAI 2023
ViewCLR: Learning Self-Supervised Video Representation for Unseen Viewpoints WACV 2023
Active Vision Reinforcement Learning under Limited Visual Observability NIPS 2023
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control CORL 2023
Video Question Answering with Iterative Video-Text Co-Tokenization ECCV 2022
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection CVPR 2022
Self-Supervised Video Transformer CVPR 2022
TRITON: Neural Neural Textures for Better Sim2Real CORL 2022
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning ECCV 2022
Recognizing Actions in Videos From Unseen Viewpoints CVPR 2021
4D-Net for Learned Multi-Modal Alignment ICCV 2021
Coarse-Fine Networks for Temporal Activity Detection in Videos CVPR 2021
Evolving Losses for Unsupervised Video Representation Learning CVPR 2020
Differentiable Grammars for Videos AAAI 2020
Adversarial Generative Grammars for Human Activity Prediction ECCV 2020
AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification ECCV 2020
Password-conditioned Anonymization and Deanonymization with Face Identity Transformers ECCV 2020
AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material - ECCV 2020
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures ICLR 2020
Model-based Behavioral Cloning with Future Image Similarity Learning CORL 2019
Representation Flow for Action Recognition CVPR 2019
Evolving Space-Time Neural Architectures for Videos ICCV 2019
Learning to Anonymize Faces for Privacy Preserving Action Detection ECCV 2018
Learning Latent Super-Events to Detect Multiple Activities in Videos CVPR 2018
Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos ECCV 2018
Identifying First-Person Camera Wearers in Third-Person Videos CVPR 2017
Pooled Motion Features for First-Person Videos CVPR 2015
First-Person Activity Recognition: What Are They Doing to Me? CVPR 2013