Wei Xu
Artificial Intelligence · Nature · 2003–2020
A researcher in the Science corpus: 50 papers; trusts 3,071 researchers and is trusted by 8,892 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 658 citations into it; #508 of 36,961 by trust here, #868 by citations
- Computer Vision and Pattern Recognition — 598 citations into it; #348 of 21,973 by trust here, #380 by citations
- Natural Language Processing — 298 citations into it; #259 of 5,725 by trust here, #285 by citations
- Electrical and Electronic Engineering — 162 citations into it; #12,561 of 16,595 by trust here, #3,231 by citations
- Model Architectures — 142 citations into it; #249 of 2,288 by trust here, #426 by citations
- Multimodal Learning — 84 citations into it; #52 of 1,215 by trust here, #97 by citations
- Aerospace Engineering — 83 citations into it; #2,637 of 6,431 by trust here, #1,392 by citations
- Optimization & Training — 80 citations into it; #583 of 2,605 by trust here, #1,989 by citations
Whom Wei Xu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Yann LeCun
- Alex Krizhevsky
- Ilya Sutskever
- Kaiming He
- Diederik P. Kingma
- Alex Graves
- Karen Simonyan
- Oriol Vinyals
Who trusts Wei Xu overall
- Deng Cai
- L. Eon Bottou
- Xiaofei He
- Yoshua Bengio
- Qi Wu
- Charu C. Aggarwal
- Chunhua Shen
- Zhe Gan
- Dacheng Tao
- Ruslan Salakhutdinov
Papers from Wei Xu's perspective
Ordered by how strongly the researchers Wei Xu 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
- Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN) (2014) — 1,283 citations
- 3D Convolutional Neural Networks for Human Action Recognition (2010)
- Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question (2015) — 531 citations
- Attention to Scale: Scale-Aware Semantic Image Segmentation (2015) — 1,391 citations
- Explain Images with Multimodal Recurrent Neural Networks (2014) — 405 citations
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks (2015) — 581 citations
- ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering (2015) — 297 citations
- Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation (2016) — 224 citations
- Bidirectional LSTM-CRF Models for Sequence Tagging (2015) — 4,469 citations
- Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks (2015) — 398 citations
- End-to-end learning of semantic role labeling using recurrent neural networks (2015) — 360 citations
- Interactive Grounded Language Acquisition and Generalization in a 2D World (2018) — 80 citations
- Document clustering based on non-negative matrix factorization (2003) — 2,153 citations
- CNN-RNN: A Unified Framework for Multi-label Image Classification (2016) — 1,254 citations
- Human Tracking Using Convolutional Neural Networks (2010) — 353 citations
- Semi-Supervised Learning for Neural Machine Translation (2016) — 261 citations
- A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment (2017) — 26 citations
- Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks (2008) — 177 citations
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering (2016) — 104 citations
- Dynamic Computational Time for Visual Attention (2017) — 117 citations