Hongsheng Li
Computer Vision and Pattern Recognition · 2010–2024
A researcher in the Science corpus: 72 papers; trusts 4,483 researchers and is trusted by 4,807 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 2,926 citations into it; #659 of 21,973 by trust here, #269 by citations
- Artificial Intelligence — 1,721 citations into it; #6,307 of 36,961 by trust here, #1,622 by citations
- Multimodal Learning — 431 citations into it; #525 of 1,215 by trust here, #204 by citations
- Model Architectures — 426 citations into it; #1,877 of 2,288 by trust here, #863 by citations
- Aerospace Engineering — 319 citations into it
- Evaluation & Benchmarks — 267 citations into it
- Representation & Self-Supervised Learning — 241 citations into it
- Large Language Models — 234 citations into it
Whom Hongsheng Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Ilya Sutskever
- Christian Szegedy
- Yoshua Bengio
- Karen Simonyan
- Yann LeCun
Who trusts Hongsheng Li overall
- Wanli Ouyang
- Xiaogang Wang
- Liang Zheng
- Vishwanath A. Sindagi
- Guanbin Li
- Xiatian Zhu
- Yi Yang
- Zhedong Zheng
- Christoph Feichtenhofer
- Peng Gao
Papers from Hongsheng Li's perspective
Ordered by how strongly the researchers Hongsheng Li 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
- StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks (2016) — 2,951 citations
- StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks (2017) — 1,190 citations
- PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud (2018) — 2,940 citations
- Efficient Attention: Attention with Linear Complexities (2018) — 772 citations
- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014) — 165 citations
- Object Detection from Video Tubelets with Convolutional Neural Networks (2016) — 389 citations
- CLIP-Adapter: Better Vision-Language Models with Feature Adapters (2021) — 1,792 citations
- Saliency detection by multi-context deep learning (2015) — 950 citations
- Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification (2016) — 996 citations
- DeepID-Net: Deformable deep convolutional neural networks for object detection (2014) — 450 citations
- LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention (2023) — 1,040 citations
- Learning Feature Pyramids for Human Pose Estimation (2017) — 525 citations
- T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos (2016) — 526 citations
- Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering (2018) — 416 citations
- Fast Convergence of DETR with Spatially Modulated Co-Attention (2021) — 404 citations
- Cross-scene crowd counting via deep convolutional neural networks (2015) — 1,185 citations
- Structured Feature Learning for Pose Estimation (2016) — 269 citations
- Object Detection in Videos with Tubelet Proposal Networks (2017) — 198 citations
- LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model (2023) — 758 citations
- Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis (2019) — 231 citations