Ruoming Pang
Artificial Intelligence · 2004–2022
A researcher in the Science corpus: 34 papers; trusts 1,940 researchers and is trusted by 3,088 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 875 citations into it; #946 of 36,961 by trust here, #464 by citations
- Computer Vision and Pattern Recognition — 454 citations into it; #992 of 21,973 by trust here, #844 by citations
- Signal Processing — 291 citations into it; #769 of 7,592 by trust here, #99 by citations
- Speech & Audio — 285 citations into it; #76 of 1,080 by trust here, #22 by citations
- Model Architectures — 219 citations into it; #1,786 of 2,288 by trust here, #744 by citations
- Natural Language Processing — 207 citations into it; #1,898 of 5,725 by trust here, #432 by citations
- Optimization & Training — 105 citations into it
- Efficiency & Compression — 101 citations into it; #44 of 1,273 by trust here, #25 by citations
Whom Ruoming Pang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Graves
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Ross B. Girshick
- Ilya Sutskever
- Yann LeCun
- Karen Simonyan
Who trusts Ruoming Pang overall
- Mingxing Tan
- Yu Zhang
- Quoc V. Le
- Xu Tan
- Jiahui Yu
- Jinyu Li
- Xiangxiang Chu
- Chien-Yao Wang
- Ye Jia
- Yi Ren
Papers from Ruoming Pang's perspective
Ordered by how strongly the researchers Ruoming Pang 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- MnasNet: Platform-Aware Neural Architecture Search for Mobile (2018) — 3,454 citations
- Searching for MobileNetV3 (2019) — 9,744 citations
- EfficientDet: Scalable and Efficient Object Detection (2019) — 7,168 citations
- NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019) — 1,781 citations
- Vector-quantized Image Modeling with Improved VQGAN (2021) — 809 citations
- Conformer: Convolution-augmented Transformer for Speech Recognition (2020) — 4,195 citations
- GSPMD: General and Scalable Parallelization for ML Computation Graphs (2021) — 188 citations
- Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions (2017) — 3,120 citations
- Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (2018) — 963 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition (2020) — 334 citations
- Hierarchical Generative Modeling for Controllable Speech Synthesis (2018) — 295 citations
- Domain Adaptive Transfer Learning with Specialist Models (2018) — 116 citations
- w2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training (2021) — 560 citations
- ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context (2020) — 302 citations
- Streaming End-to-end Speech Recognition for Mobile Devices (2018) — 676 citations
- Monotonic Infinite Lookback Attention for Simultaneous Machine Translation (2019) — 218 citations
- BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition (2021) — 208 citations
- Semi-supervised Training for End-to-end Models via Weak Distillation (2019) — 54 citations
- Co-training Transformer with Videos and Images Improves Action Recognition (2021) — 63 citations