Fei Sha
Artificial Intelligence · 2003–2022
A researcher in the Science corpus: 46 papers; trusts 4,061 researchers and is trusted by 6,556 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,166 citations into it; #418 of 36,961 by trust here, #789 by citations
- Computer Vision and Pattern Recognition — 793 citations into it; #563 of 21,973 by trust here, #915 by citations
- Representation & Self-Supervised Learning — 333 citations into it; #109 of 3,156 by trust here, #169 by citations
- Natural Language Processing — 236 citations into it; #424 of 5,725 by trust here, #1,373 by citations
- Optimization & Training — 140 citations into it
- Evaluation & Benchmarks — 123 citations into it
- Model Architectures — 115 citations into it; #2,025 of 2,288 by trust here, #1,699 by citations
- Reinforcement Learning — 92 citations into it; #617 of 2,250 by trust here, #1,256 by citations
Whom Fei Sha trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Diederik P. Kingma
- Kaiming He
- Ilya Sutskever
- Yann LeCun
- Ross B. Girshick
- Alex Graves
- Oriol Vinyals
Who trusts Fei Sha overall
- Han-Jia Ye
- Mingsheng Long
- Andrew McCallum
- Yoshua Bengio
- Trevor Darrell
- Ronan Collobert
- Mark W. Schmidt
- Trevor Cohn
- Kristen Grauman
- Judy Hoffman
Papers from Fei Sha's perspective
Ordered by how strongly the researchers Fei Sha 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)
- 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
- Geodesic flow kernel for unsupervised domain adaptation (2012) — 2,444 citations
- Shallow Parsing with Conditional Random Fields (2003) — 1,567 citations
- Marginalized Denoising Autoencoders for Domain Adaptation (2012) — 838 citations
- Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification (2007) — 429 citations
- An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild (2016) — 619 citations
- Synthesized Classifiers for Zero-Shot Learning (2016) — 755 citations
- Learning with Whom to Share in Multi-task Feature Learning (2011) — 404 citations
- Attention Correctness in Neural Image Captioning (2016) — 229 citations
- Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning (2016) — 181 citations
- Deformable Spatial Pyramid Matching for Fast Dense Correspondences (2013) — 266 citations
- Sharing features between objects and their attributes (2011) — 125 citations
- Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation (2013) — 521 citations
- Reshaping Visual Datasets for Domain Adaptation (2013) — 142 citations
- Cross-Modal and Hierarchical Modeling of Video and Text (2018) — 208 citations
- Learning Embedding Adaptation for Few-Shot Learning (2018) — 90 citations
- Learning a kernel matrix for nonlinear dimensionality reduction (2004) — 595 citations
- DiscLDA: Discriminative Learning for Dimensionality Reduction and Classification (2008) — 442 citations
- Video Summarization with Long Short-Term Memory (2016) — 783 citations
- Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions (2018) — 830 citations
- Multi-Task Learning for Sequence Tagging: An Empirical Study (2018) — 68 citations