Suha Kwak

Computer Vision and Pattern Recognition · 2014–2020

A researcher in the Science corpus: 9 papers; trusts 1,580 researchers and is trusted by 367 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 267 citations into it; #2,129 of 21,575 by trust here, #3,345 by citations
• Artificial Intelligence — 130 citations into it; #8,660 of 35,345 by trust here, #12,387 by citations
• Representation & Self-Supervised Learning — 48 citations into it; #1,072 of 3,145 by trust here, #2,012 by citations
• Aerospace Engineering — 27 citations into it; #4,413 of 6,421 by trust here, #2,921 by citations
• Evaluation & Benchmarks — 26 citations into it
• Model Architectures — 16 citations into it
• Optimization & Training — 11 citations into it
• Media Technology — 10 citations into it

Whom Suha Kwak trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Kaiming He
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Ross B. Girshick
5. Diederik P. Kingma
6. Karen Simonyan
7. Yoshua Bengio
8. Andrew Zisserman
9. Yann LeCun
10. Ilya Sutskever

Who trusts Suha Kwak overall

1. Nikita Araslanov
2. Sanghyun Jo
3. Martin Lohmann
4. Jiwoon Ahn
5. Kai Kang
6. Saeid Motiian
7. Hyeonseob Nam
8. Guolei Sun
9. Luowei Zhou
10. Huy V. Vo

Papers from Suha Kwak's perspective

Ordered by how strongly the researchers Suha Kwak trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015) — 288 citations
• Unsupervised Object Discovery and Tracking in Video Collections (2015) — 127 citations
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015) — 852 citations
• Weakly Supervised Semantic Segmentation Using Web-Crawled Videos (2017) — 161 citations
• Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation (2018) — 898 citations
• Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations (2019) — 654 citations
• Domain-Specific Batch Normalization for Unsupervised Domain Adaptation (2019) — 435 citations
• Proxy Anchor Loss for Deep Metric Learning (2020) — 468 citations
• Object Localization based on Structural SVM using Privileged Information (2014) — 46 citations