Xiang-Yang Li

Computer Vision and Pattern Recognition · 2017–2024

A researcher in the Science corpus: 18 papers; trusts 1,270 researchers and is trusted by 90 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 483 citations into it; #3,384 of 21,575 by trust here, #2,587 by citations
• Artificial Intelligence — 423 citations into it; #22,975 of 35,345 by trust here, #8,365 by citations
• Model Architectures — 143 citations into it; #960 of 2,278 by trust here, #874 by citations
• Signal Processing — 71 citations into it
• Natural Language Processing — 63 citations into it
• Optimization & Training — 62 citations into it; #2,398 of 2,601 by trust here, #2,112 by citations
• Evaluation & Benchmarks — 36 citations into it
• Media Technology — 34 citations into it; #3,442 of 3,621 by trust here, #1,859 by citations

Whom Xiang-Yang Li trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Kaiming He
2. Ross B. Girshick
3. Alex Krizhevsky
4. Geoffrey E. Hinton
5. Shaoqing Ren
6. Yoshua Bengio
7. Ilya Sutskever
8. Diederik P. Kingma
9. Christian Szegedy
10. Tsung-Yi Lin

Who trusts Xiang-Yang Li overall

1. Chien-Yao Wang
2. Wenhai Wang
3. Xingyi Zhou
4. Yimian Dai
5. Qing-Long Zhang
6. Hongpeng Liao
7. Enze Xie
8. Ping Luo
9. Lucas Tabelini
10. Minghui Liao

Papers from Xiang-Yang Li's perspective

Ordered by how strongly the researchers Xiang-Yang Li trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
8. Gradient-based learning applied to document recognition
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Selective Kernel Networks (2019) — 2,712 citations
• PVT v2: Improved baselines with Pyramid Vision Transformer (2021) — 2,512 citations
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection (2020) — 1,924 citations
• Shape Robust Text Detection With Progressive Scale Expansion Network (2018) — 722 citations
• Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift (2018) — 331 citations
• Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation (2018) — 234 citations
• Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection (2020) — 334 citations
• Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit (2020) — 321 citations
• NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models (2024) — 403 citations
• PromptTTS 2: Describing and Generating Voices with Text Prompt (2023) — 87 citations
• Large Selective Kernel Network for Remote Sensing Object Detection (2023) — 602 citations
• Curriculum Temperature for Knowledge Distillation (2022) — 304 citations
• Learning to Reweight with Deep Interactions (2021) — 6 citations
• MBNET: MOS Prediction for Synthesized Speech with Mean-Bias Network (2021) — 132 citations
• Searching Better Architectures for Neural Machine Translation (2020) — 27 citations
• Unsupervised Pivot Translation for Distant Languages (2019) — 32 citations
• Learning to Teach (2018) — 17 citations
• Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal (2017) — 517 citations