Ivor Wai-Hung Tsang
Artificial Intelligence · 2003–2020
A researcher in the Science corpus: 34 papers; trusts 2,256 researchers and is trusted by 2,451 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 482 citations into it; #1,509 of 36,961 by trust here, #1,591 by citations
- Computer Vision and Pattern Recognition — 373 citations into it; #1,086 of 21,973 by trust here, #1,945 by citations
- Representation & Self-Supervised Learning — 120 citations into it; #202 of 3,156 by trust here, #273 by citations
- Optimization & Training — 78 citations into it; #2,352 of 2,605 by trust here, #787 by citations
- Statistics and Probability — 61 citations into it
- Statistical Learning Theory — 53 citations into it
- Computational Mechanics — 51 citations into it; #1,149 of 10,021 by trust here, #1,787 by citations
- Evaluation & Benchmarks — 50 citations into it; #2,211 of 3,155 by trust here, #2,979 by citations
Whom Ivor Wai-Hung Tsang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Bernhard Schölkopf
- David G. Lowe
- Diederik P. Kingma
- Yann LeCun
- Kaiming He
- Alex Smola
- Andrew Zisserman
Who trusts Ivor Wai-Hung Tsang overall
- Mingsheng Long
- Wen Li
- Gabriella Csurka
- Judy Hoffman
- Dong Xu
- Lixin Duan
- Kate Saenko
- Baochen Sun
- Jianmin Wang
- Li Niu
Papers from Ivor Wai-Hung Tsang's perspective
Ordered by how strongly the researchers Ivor Wai-Hung Tsang 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Domain Adaptation via Transfer Component Analysis (2009) — 4,470 citations
- Visual event recognition in videos by learning from web data (2010) — 437 citations
- Domain Transfer SVM for video concept detection (2009) — 305 citations
- Learning with Augmented Features for Heterogeneous Domain Adaptation (2012) — 357 citations
- Domain adaptation from multiple sources via auxiliary classifiers (2009) — 338 citations
- Co-teaching: Robust training of deep neural networks with extremely noisy labels (2018) — 2,654 citations
- Local features are not lonely – Laplacian sparse coding for image classification (2010) — 472 citations
- The pre-image problem in kernel methods (2003) — 504 citations
- Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and Applications (2013) — 369 citations
- Spectral Embedded Clustering: A Framework for In-Sample and Out-of-Sample Spectral Clustering (2011) — 318 citations
- Domain Transfer Multiple Kernel Learning (2012) — 534 citations
- Large Margin Metric Learning for Multi-Label Prediction (2015) — 90 citations
- Kernel Sparse Representation for Image Classification and Face Recognition (2010) — 386 citations
- Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation (2014) — 428 citations
- Region-Based Saliency Detection and Its Application in Object Recognition (2014) — 329 citations
- How does Disagreement Help Generalization against Label Corruption? (2019) — 972 citations
- A Unified Feature Selection Framework for Graph Embedding on High Dimensional Data (2015) — 35 citations
- The Emerging Trends of Multi-Label Learning (2020) — 387 citations
- Curriculum Loss: Robust Learning and Generalization against Label Corruption (2019) — 195 citations
- Degeneration in VAE: in the Light of Fisher Information Loss (2018) — 18 citations