Yu-Wing Tai
Computer Vision and Pattern Recognition · 2005–2023
A researcher in the Science corpus: 19 papers; trusts 2,562 researchers and is trusted by 792 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 480 citations into it; #2,051 of 21,973 by trust here, #1,994 by citations
- Artificial Intelligence — 171 citations into it; #12,366 of 36,961 by trust here, #8,478 by citations
- Model Architectures — 58 citations into it
- Representation & Self-Supervised Learning — 48 citations into it
- Computational Mechanics — 35 citations into it
- Evaluation & Benchmarks — 34 citations into it; #2,851 of 3,155 by trust here, #2,633 by citations
- Media Technology — 34 citations into it; #1,240 of 3,630 by trust here, #643 by citations
- Aerospace Engineering — 28 citations into it
Whom Yu-Wing Tai trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yann LeCun
- Yoshua Bengio
- Diederik P. Kingma
- Karen Simonyan
- Ilya Sutskever
- David G. Lowe
Who trusts Yu-Wing Tai overall
- Michael Hirsch
- Wenguan Wang
- Gustav Larsson
- Ho Kei Cheng
- He He
- Huchuan Lu
- Li Xu
- Tiantian Wang
- Subeesh Vasu
- Ali Borji
Papers from Yu-Wing Tai's perspective
Ordered by how strongly the researchers Yu-Wing Tai 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)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- RMPE: Regional Multi-person Pose Estimation (2016) — 1,772 citations
- Semantic colorization with internet images (2011) — 268 citations
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures (2016) — 967 citations
- Accurate Single Stage Detector Using Recurrent Rolling Convolution (2017) — 297 citations
- High quality depth map upsampling for 3D-TOF cameras (2011) — 540 citations
- Richardson-Lucy Deblurring for Scenes under a Projective Motion Path (2011) — 331 citations
- FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation (2019) — 325 citations
- Local color transfer via probabilistic segmentation by expectation-maximization (2005) — 408 citations
- Super resolution using edge prior and single image detail synthesis (2010) — 345 citations
- Segment Anything in High Quality (2023) — 655 citations
- Deep High Dynamic Range Imaging with Large Foreground Motions (2017) — 301 citations
- Learning Video Object Segmentation From Unlabeled Videos (2020) — 154 citations
- Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation (2021) — 382 citations
- Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers (2021) — 227 citations
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (2019) — 642 citations
- High-resolution hyperspectral imaging via matrix factorization (2011) — 335 citations
- Deep Saliency with Encoded Low Level Distance Map and High Level Features (2016) — 464 citations
- Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution (2018) — 75 citations
- Accurate depth map estimation from a lenslet light field camera (2015) — 495 citations