Xingjun Ma

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 18 papers; trusts 887 researchers and is trusted by 29 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 544 citations into it; #6,493 of 35,345 by trust here, #3,059 by citations
• Computer Vision and Pattern Recognition — 293 citations into it; #13,803 of 21,575 by trust here, #5,205 by citations
• Safety, Robustness & Interpretability — 293 citations into it; #1,575 of 2,251 by trust here, #831 by citations
• Signal Processing — 107 citations into it
• Optimization & Training — 76 citations into it
• Privacy & Security — 76 citations into it; #690 of 709 by trust here, #570 by citations
• Model Architectures — 58 citations into it
• Federated & Distributed Learning — 45 citations into it; #317 of 319 by trust here, #282 by citations

Whom Xingjun Ma trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Geoffrey E. Hinton
4. Yann LeCun
5. Christian Szegedy
6. Yoshua Bengio
7. Ian J. Goodfellow
8. Ilya Sutskever
9. Diederik P. Kingma
10. Ross B. Girshick

Who trusts Xingjun Ma overall

1. Yisen Wang
2. Dongxian Wu
3. Junnan Li
4. Yige Li
5. David Stutz
6. Lingjuan Lyu
7. Kimin Lee
8. James Bailey
9. Xiaobo Xia
10. Fanchao Qi

Papers from Xingjun Ma's perspective

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

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

Their papers

• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality (2018) — 849 citations
• Dimensionality-Driven Learning with Noisy Labels (2018) — 475 citations
• WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection (2020) — 577 citations
• Iterative Learning with Open-set Noisy Labels (2018) — 357 citations
• On the Convergence and Robustness of Adversarial Training (2021) — 386 citations
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems (2019) — 547 citations
• Normalized Loss Functions for Deep Learning with Noisy Labels (2020) — 563 citations
• Black-box Adversarial Attacks on Video Recognition Models (2019) — 171 citations
• Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets (2020) — 364 citations
• Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks (2021) — 575 citations
• Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression (2021) — 333 citations
• Anti-Backdoor Learning: Training Clean Models on Poisoned Data (2021) — 473 citations
• Improving Adversarial Robustness Requires Revisiting Misclassified Examples (2020) — 849 citations
• Privacy and Robustness in Federated Learning: Attacks and Defenses (2020) — 538 citations
• Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks (2020) — 617 citations
• Clean-Label Backdoor Attacks on Video Recognition Models (2020) — 324 citations
• Symmetric Cross Entropy for Robust Learning With Noisy Labels (2019) — 1,167 citations
• Towards Fair and Privacy-Preserving Federated Deep Models (2019) — 244 citations