Xiangyu Yue
Computer Vision and Pattern Recognition · IEEE International Conference on Computer Vision · 2017–2023
A researcher in the Science corpus: 13 papers; trusts 968 researchers and is trusted by 23 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 468 citations into it; #5,535 of 21,575 by trust here, #2,872 by citations
- Artificial Intelligence — 388 citations into it; #18,542 of 35,345 by trust here, #4,860 by citations
- Representation & Self-Supervised Learning — 129 citations into it
- Evaluation & Benchmarks — 62 citations into it
- Aerospace Engineering — 53 citations into it
- Computational Mechanics — 44 citations into it
- Model Architectures — 40 citations into it
- Radiology, Nuclear Medicine and Imaging — 39 citations into it
Whom Xiangyu Yue trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Ross B. Girshick
- Yoshua Bengio
- Yann LeCun
- Karen Simonyan
- Ilya Sutskever
- Andrew Zisserman
Who trusts Xiangyu Yue overall
- Bichen Wu
- Sergey I. Nikolenko
- Kaiyang Zhou
- Myeongjin Kim
- Chenfeng Xu
- Jiaxing Huang
- Xiaoliang Dai
- Jindong Wang
- Shujun Wang
- Jens Behley
Papers from Xiangyu Yue's perspective
Ordered by how strongly the researchers Xiangyu Yue 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
- Gradient-based learning applied to document recognition
- 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)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions (2017) — 401 citations
- LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model (2023) — 758 citations
- SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud (2017) — 932 citations
- ImageBind-LLM: Multi-modality Instruction Tuning (2023) — 181 citations
- SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud (2018) — 726 citations
- SqueezeNext: Hardware-Aware Neural Network Design (2018) — 329 citations
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (2020) — 610 citations
- Self-Supervised Pretraining Improves Self-Supervised Pretraining (2021) — 137 citations
- Unsupervised Point Cloud Pre-training via Occlusion Completion (2020) — 336 citations
- A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (2020) — 338 citations
- Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data (2019) — 472 citations
- Counterexample-Guided Data Augmentation (2018) — 68 citations
- Scenic: a language for scenario specification and scene generation (2018) — 325 citations