Sanghyun Woo
Computer Vision and Pattern Recognition · 2017–2024
A researcher in the Science corpus: 9 papers; trusts 1,335 researchers and is trusted by 154 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 370 citations into it; #2,883 of 21,575 by trust here, #2,033 by citations
- Artificial Intelligence — 226 citations into it; #4,237 of 35,345 by trust here, #2,798 by citations
- Model Architectures — 76 citations into it; #368 of 2,278 by trust here, #360 by citations
- Evaluation & Benchmarks — 41 citations into it
- Representation & Self-Supervised Learning — 31 citations into it
- Optimization & Training — 26 citations into it
- Generative Models — 15 citations into it
- Radiology, Nuclear Medicine and Imaging — 11 citations into it; #2,049 of 3,265 by trust here, #1,316 by citations
Whom Sanghyun Woo trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Alex Krizhevsky
- Geoffrey E. Hinton
- Shaoqing Ren
- Christian Szegedy
- Karen Simonyan
- Yann LeCun
- Yoshua Bengio
- Ilya Sutskever
Who trusts Sanghyun Woo overall
- Jongchan Park
- Juan R. Terven
- Zhongzhan Huang
- Qibin Hou
- Md Mostafijur Rahman
- Irwan Bello
- Chun-Fu Chen
- Nantheera Anantrasirichai
- Junsuk Choe
- David W. Romero
Papers from Sanghyun Woo's perspective
Ordered by how strongly the researchers Sanghyun Woo trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- CBAM: Convolutional Block Attention Module (2018) — 24,594 citations
- Video Panoptic Segmentation (2020) — 205 citations
- BAM: Bottleneck Attention Module (2018) — 1,311 citations
- ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders (2023) — 1,840 citations
- Deep Video Inpainting (2019) — 235 citations
- Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs (2024) — 900 citations
- StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection (2017) — 101 citations
- LinkNet: Relational Embedding for Scene Graph (2018) — 158 citations
- Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation (2021) — 41 citations