Siwei Lyu
Computer Vision and Pattern Recognition · 2002–2020
A researcher in the Science corpus: 31 papers; trusts 2,106 researchers and is trusted by 1,977 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 621 citations into it; #1,243 of 21,973 by trust here, #1,263 by citations
- Artificial Intelligence — 234 citations into it; #2,635 of 36,961 by trust here, #10,044 by citations
- Generative Models — 64 citations into it; #1,687 of 1,963 by trust here, #1,071 by citations
- Model Architectures — 55 citations into it
- Signal Processing — 50 citations into it; #940 of 7,592 by trust here, #3,788 by citations
- Evaluation & Benchmarks — 47 citations into it
- Media Technology — 43 citations into it; #819 of 3,630 by trust here, #1,932 by citations
- Aerospace Engineering — 38 citations into it
Whom Siwei Lyu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Eero P. Simoncelli
- Geoffrey E. Hinton
- Aapo Hyvärinen
- Kaiming He
- Diederik P. Kingma
- Karen Simonyan
- Alex Krizhevsky
- David J. Heeger
- Hany Farid
- Yann LeCun
Who trusts Siwei Lyu overall
- Hany Farid
- Jessica J. Fridrich
- Johannes Ballé
- Balaji Lakshminarayanan
- Pascal Vincent
- Valero Laparra
- Tomás Pevný
- Yang Song
- Arash Vahdat
- Luisa Verdoliva
Papers from Siwei Lyu's perspective
Ordered by how strongly the researchers Siwei Lyu 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- 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
- The Visual Object Tracking VOT2015 Challenge Results (2015) — 901 citations
- The Visual Object Tracking VOT2016 Challenge Results (2016) — 773 citations
- Object-Driven Text-To-Image Synthesis via Adversarial Training (2019) — 324 citations
- Nonlinear image representation using divisive normalization (2008) — 171 citations
- Interpretation and Generalization of Score Matching (2009) — 170 citations
- Exposing DeepFake Videos By Detecting Face Warping Artifacts (2018) — 1,204 citations
- UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015) — 749 citations
- A digital technique for art authentication (2004) — 211 citations
- Multi-Scale Structure-Aware Network for Human Pose Estimation (2018) — 298 citations
- Unifying Non-Maximum Likelihood Learning Objectives with Minimum KL Contraction (2011) — 21 citations
- Modeling Multiscale Subbands of Photographic Images with Fields of Gaussian Scale Mixtures (2009) — 89 citations
- The Visual Object Tracking VOT2017 Challenge Results (2017) — 301 citations
- Exposing Deep Fakes Using Inconsistent Head Poses (2018) — 1,129 citations
- Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics (2019) — 1,748 citations
- In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking (2018) — 898 citations
- Celeb-DF: A New Dataset for DeepFake Forensics (2019) — 211 citations
- Divisive Normalization: Justification and Effectiveness as Efficient Coding Transform (2010) — 26 citations
- Adaptive RNN Tree for Large-Scale Human Action Recognition (2017) — 104 citations
- Invisible Backdoor Attack with Sample-Specific Triggers (2020) — 680 citations
- Guided Attention Network for Object Detection and Counting on Drones (2019) — 75 citations