Michael S. Ryoo
Computer Vision and Pattern Recognition · 2006–2023
A researcher in the Science corpus: 21 papers; trusts 2,389 researchers and is trusted by 3,210 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 578 citations into it; #894 of 21,973 by trust here, #1,400 by citations
- Artificial Intelligence — 466 citations into it; #1,906 of 36,961 by trust here, #2,304 by citations
- Reinforcement Learning — 97 citations into it; #1,886 of 2,250 by trust here, #929 by citations
- Model Architectures — 84 citations into it
- Multimodal Learning — 77 citations into it
- Representation & Self-Supervised Learning — 72 citations into it
- Control and Systems Engineering — 62 citations into it; #6,573 of 8,519 by trust here, #7,395 by citations
- Evaluation & Benchmarks — 59 citations into it
Whom Michael S. Ryoo trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ross B. Girshick
- Piotr Doll'ar
- David G. Lowe
- Andrew Zisserman
- Karen Simonyan
- Yoshua Bengio
- Diederik P. Kingma
Who trusts Michael S. Ryoo overall
- Antonino Furnari
- Kris M. Kitani
- Ryo Yonetani
- Tsz-Ho Yu
- Kristen Grauman
- Alonso Patron-Perez
- Yin Li
- Yu Kong
- Qiuhong Ke
- Jianfang Hu
Papers from Michael S. Ryoo's perspective
Ordered by how strongly the researchers Michael S. Ryoo trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022) — 742 citations
- RT-1: Robotics Transformer for Real-World Control at Scale (2022) — 2,545 citations
- Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities (2009) — 624 citations
- First-Person Activity Recognition: What Are They Doing to Me? (2013) — 316 citations
- Human activity prediction: Early recognition of ongoing activities from streaming videos (2011) — 600 citations
- Evolving Losses for Unsupervised Video Representation Learning (2020) — 149 citations
- Recognition of Composite Human Activities through Context-Free Grammar Based Representation (2006) — 295 citations
- Pooled motion features for first-person videos (2014) — 186 citations
- TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? (2021) — 181 citations
- Human activity analysis (2011) — 1,339 citations
- Open-vocabulary Queryable Scene Representations for Real World Planning (2022) — 257 citations
- Learning Real-World Robot Policies by Dreaming (2018) — 33 citations
- Evolving Space-Time Neural Architectures for Videos (2018) — 62 citations
- AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures (2019) — 110 citations
- Hierarchical Recognition of Human Activities Interacting with Objects (2007) — 62 citations
- Evolving Losses for Unlabeled Video Representation Learning (2019) — 7 citations
- Representation Flow for Action Recognition (2018) — 165 citations
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control (2023) — 3,674 citations
- Hybrid Random Features (2021) — 27 citations
- AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification (2020) — 54 citations