Kevin J. Shih
Computer Vision and Pattern Recognition · 2013–2021
A researcher in the Science corpus: 11 papers; trusts 1,404 researchers and is trusted by 1,360 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 202 citations into it; #1,567 of 21,973 by trust here, #2,803 by citations
- Artificial Intelligence — 137 citations into it; #5,997 of 36,961 by trust here, #7,227 by citations
- Generative Models — 47 citations into it; #1,829 of 1,963 by trust here, #1,465 by citations
- Natural Language Processing — 46 citations into it
- Model Architectures — 31 citations into it
- Speech & Audio — 28 citations into it; #972 of 1,080 by trust here, #755 by citations
- Signal Processing — 27 citations into it; #7,030 of 7,592 by trust here, #3,677 by citations
- Multimodal Learning — 16 citations into it
Whom Kevin J. Shih trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Kaiming He
- Ilya Sutskever
- Ross B. Girshick
- Yann LeCun
- Karen Simonyan
- Alex Graves
Who trusts Kevin J. Shih overall
- Zhou Zhao
- Huijuan Xu
- Xinlei Chen
- Damien Teney
- Abhinav Kumar Gupta
- Dong Huk Park
- Alexander Gerhard Schwing
- Hyeonwoo Noh
- Medhini Narasimhan
- Badri N. Patro
Papers from Kevin J. Shih's perspective
Ordered by how strongly the researchers Kevin J. Shih 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Where to Look: Focus Regions for Visual Question Answering (2015) — 487 citations
- Image Inpainting for Irregular Holes Using Partial Convolutions (2018) — 2,284 citations
- Learning Collections of Part Models for Object Recognition (2013)
- Learning Interpretable Spatial Operations in a Rich 3D Blocks World (2017) — 65 citations
- Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization (2015) — 43 citations
- Improving Semantic Segmentation via Video Propagation and Label Relaxation (2018) — 415 citations
- Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis (2020) — 135 citations
- Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos (2020) — 35 citations
- One TTS Alignment to Rule Them All (2021) — 106 citations
- RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis (2021)
- Partial Convolution based Padding (2018) — 101 citations