Seong Joon Oh
Computer Vision and Pattern Recognition · 2015–2023
A researcher in the Science corpus: 19 papers; trusts 2,637 researchers and is trusted by 1,595 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 570 citations into it; #1,434 of 21,973 by trust here, #1,445 by citations
- Artificial Intelligence — 446 citations into it; #5,013 of 36,961 by trust here, #2,647 by citations
- Safety, Robustness & Interpretability — 102 citations into it; #1,224 of 2,259 by trust here, #1,292 by citations
- Evaluation & Benchmarks — 86 citations into it; #3,137 of 3,155 by trust here, #2,228 by citations
- Model Architectures — 71 citations into it
- Signal Processing — 68 citations into it; #4,667 of 7,592 by trust here, #3,677 by citations
- Optimization & Training — 61 citations into it; #889 of 2,605 by trust here, #295 by citations
- Representation & Self-Supervised Learning — 52 citations into it
Whom Seong Joon Oh trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Christian Szegedy
- Karen Simonyan
- Ilya Sutskever
- Ross B. Girshick
- Yoshua Bengio
- Yann LeCun
- Diederik P. Kingma
Who trusts Seong Joon Oh overall
- Qianru Sun
- Bernt Schiele
- Mario Fritz
- Tribhuvanesh Orekondy
- Zhiqiang Shen
- Ahmed Salem
- Jiwoon Ahn
- Rodrigo Benenson
- Ayush Kumar Tewari
- Maria Rigaki
Papers from Seong Joon Oh's perspective
Ordered by how strongly the researchers Seong Joon Oh 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
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features (2019) — 6,079 citations
- Reliable Fidelity and Diversity Metrics for Generative Models (2020) — 603 citations
- Rethinking Spatial Dimensions of Vision Transformers (2021) — 757 citations
- Exploiting Saliency for Object Segmentation from Image Level Labels (2017) — 209 citations
- Faceless Person Recognition: Privacy Implications in Social Media (2016) — 172 citations
- Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels (2021) — 176 citations
- Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective (2017) — 169 citations
- Natural and Effective Obfuscation by Head Inpainting (2017) — 226 citations
- Person Recognition in Personal Photo Collections (2015) — 55 citations
- What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis (2019) — 570 citations
- Towards Reverse-Engineering Black-Box Neural Networks (2017) — 405 citations
- Playing repeated games with large language models (2023) — 295 citations
- Probabilistic Embeddings for Cross-Modal Retrieval (2021) — 306 citations
- Learning De-biased Representations with Biased Representations (2019) — 339 citations
- Understanding and Controlling User Linkability in Decentralized Learning (2018) — 14 citations
- Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning (2018) — 43 citations
- Person Recognition in Personal Photo Collections (2017) — 9 citations
- I-Pic: A Platform for Privacy-Compliant Image Capture (2016) — 128 citations
- Demo: I-Pic: A Platform for Privacy-Compliant Image Capture (2016) — 4 citations