Nojun Kwak
Computer Vision and Pattern Recognition · 2002–2020
A researcher in the Science corpus: 18 papers; trusts 2,243 researchers and is trusted by 168 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 329 citations into it; #3,442 of 21,973 by trust here, #2,983 by citations
- Artificial Intelligence — 289 citations into it; #3,914 of 36,961 by trust here, #4,853 by citations
- Efficiency & Compression — 91 citations into it; #338 of 1,273 by trust here, #648 by citations
- Model Architectures — 71 citations into it
- Optimization & Training — 43 citations into it; #1,407 of 2,605 by trust here, #2,316 by citations
- Representation & Self-Supervised Learning — 42 citations into it
- Natural Language Processing — 35 citations into it; #5,024 of 5,725 by trust here, #4,141 by citations
- Evaluation & Benchmarks — 29 citations into it
Whom Nojun Kwak trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Kaiming He
- Alex Krizhevsky
- Yoshua Bengio
- Yann LeCun
- Ross B. Girshick
- Diederik P. Kingma
- Karen Simonyan
- Ilya Sutskever
- Christian Szegedy
Who trusts Nojun Kwak overall
- Yudong Zhang
- Elynn Y. Chen
- Jian-Bo Yang
- Lin Wang
- Thierry Bouwmans
- Ran He
- Qinghua Hu
- Esther Robb
- Wilson Estécio Marcílio
- Morteza Noshad
Papers from Nojun Kwak's perspective
Ordered by how strongly the researchers Nojun Kwak 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- 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
- Paraphrasing Complex Network: Network Compression via Factor Transfer (2018) — 652 citations
- 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information (2016) — 172 citations
- A Comprehensive Overhaul of Feature Distillation (2019) — 759 citations
- Self-supervised pre-training and contrastive representation learning for multiple-choice video QA (2020) — 45 citations
- Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information (2018) — 226 citations
- Input Feature Selection by Mutual Information Based on Parzen Window (2002) — 650 citations
- Analysis on the Dropout Effect in Convolutional Neural Networks (2016) — 217 citations
- LSQ+: Improving low-bit quantization through learnable offsets and better initialization (2020) — 310 citations
- Principal Component Analysis Based on L1-Norm Maximization (2008) — 750 citations
- Feature-map-level Online Adversarial Knowledge Distillation (2020) — 155 citations
- Feature-Level Ensemble Knowledge Distillation for Aggregating Knowledge from Multiple Networks (2020) — 47 citations
- Consistency-based Semi-supervised Learning for Object detection (2019) — 484 citations
- Feature Fusion for Online Mutual Knowledge Distillation (2019) — 110 citations
- QKD: Quantization-aware Knowledge Distillation (2019) — 82 citations
- FEED: Feature-level Ensemble for Knowledge Distillation (2019) — 46 citations
- Enhancement of SSD by concatenating feature maps for object detection (2017) — 336 citations
- Efficient $l_{1}$ -Norm-Based Low-Rank Matrix Approximations for Large-Scale Problems Using Alternating Rectified Gradient Method (2015) — 46 citations
- Input feature selection for classification problems (2002) — 988 citations