Closed 612901 closed 1 year ago
⚠️ 抱歉,Github Actions 检测到您的网站存在违规信息,现已下架。
如果您确认已经处理了违规信息,请重新提交issues.
以下是 Github Actions 检测到的违规信息 [注: Github Actions 可能会触发网站防火墙]
Kaiming He 何恺明
Research Scientist Facebook AI Research (FAIR), Menlo Park, CA
|
I am a Research Scientist at Facebook AI Research (FAIR). My research areas include computer vision and deep learning.
|
Publications
Masked Autoencoders As Spatiotemporal Learners |
||
Exploring Plain Vision Transformer Backbones for Object Detection |
||
Benchmarking Detection Transfer Learning with Vision Transformers |
||
Masked Autoencoders Are Scalable Vision Learners |
||
An Empirical Study of Training Self-Supervised Vision Transformers |
||
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning |
||
Exploring Simple Siamese Representation Learning |
||
Graph Structure of Neural Networks |
||
Are Labels Necessary for Neural Architecture Search? |
||
Improved Baselines with Momentum Contrastive Learning |
||
Momentum Contrast for Unsupervised Visual Representation Learning |
||
PointRend: Image Segmentation as Rendering |
||
A Multigrid Method for Efficiently Training Video Models |
||
Designing Network Design Spaces |
||
Exploring Randomly Wired Neural Networks for Image Recognition |
||
SlowFast Networks for Video Recognition |
||
Deep Hough Voting for 3D Object Detection in Point Clouds |
||
TensorMask: A Foundation for Dense Object Segmentation |
||
Rethinking ImageNet Pre-training |
||
Feature Denoising for Improving Adversarial Robustness |
||
Long-Term Feature Banks for Detailed Video Understanding |
||
Panoptic Feature Pyramid Networks |
||
Panoptic Segmentation |
||
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations |
||
Group Normalization |
||
Exploring the Limits of Weakly Supervised Pretraining |
||
Non-local Neural Networks |
||
Data Distillation: Towards Omni-Supervised Learning |
||
Detecting and Recognizing Human-Object Interactions |
||
Learning to Segment Every Thing |
||
Mask R-CNN |
||
Focal Loss for Dense Object Detection |
||
Transitive Invariance for Self-supervised Visual Representation Learning |
||
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour |
||
Feature Pyramid Networks for Object Detection |
||
Aggregated Residual Transformations for Deep Neural Networks |
||
R-FCN: Object Detection via Region-based Fully Convolutional Networks |
||
Is Faster R-CNN Doing Well for Pedestrian Detection? |
||
Instance-sensitive Fully Convolutional Networks |
||
Identity Mappings in Deep Residual Networks |
||
Deep Residual Learning for Image Recognition |
||
Instance-aware Semantic Segmentation via Multi-task Network Cascades |
||
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation |
||
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks |
||
Object Detection Networks on Convolutional Feature Maps |
||
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation |
||
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification |
||
Convolutional Neural Networks at Constrained Time Cost |
||
Convolutional Feature Masking for Joint Object and Stuff Segmentation |
||
Efficient and Accurate Approximations of Nonlinear Convolutional Networks |
||
Sparse Projections for High-Dimensional Binary Codes |
||
A Geodesic-Preserving Method for Image Warping |
||
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition |
||
Learning a Deep Convolutional Network for Image Super-Resolution |
||
Graph Cuts for Supervised Binary Coding |
||
Product Sparse Coding |
||
Content-Aware Rotation |
||
Joint Inverted Indexing |
||
Constant Time Weighted Median Filtering for Stereo Matching and Beyond |
||
Rectangling Panoramic Images via Warping |
||
Optimized Product Quantization for Approximate Nearest Neighbor Search |
||
K-means Hashing: an Affinity-Preserving Quantization Method for Learning Binary Compact Codes |
||
Statistics of Patch Offsets for Image Completion |
||
Computing Nearest-Neighbor Fields via Propagation-Assisted KD-Trees |
||
A Global Sampling Method for Alpha Matting |
||
Guided Image Filtering |
||
Fast Matting using Large Kernel Matting Laplacian Matrices |
||
Single Image Haze Removal using Dark Channel Prior |
Activities
Program Chair: ICCV 2023
Area Chair: CVPR 2016, ICCV 2017, CVPR 2018, ECCV 2018, CVPR 2020, CVPR 2021, CVPR 2022
Associate Editor: IJCV 2016 - 2019
Co-organize a tutorial on Visual Recognition at ECCV 2018. slides
Co-organize a tutorial on Visual Recognition at CVPR 2018. slides
Co-organize a tutorial on Instance-level Recognition at ICCV 2017. slides
Co-organize a tutorial on Deep Learning for Objects and Scenes at CVPR 2017. slides
Invited to give a tutorial on Deep Residual Networks at ICML 2016. website
Co-organize a tutorial on Object Detection at ICCV 2015. slides
Awards and Honors
PAMI Everingham Prize, 2021
CVPR Best Paper Award, 2016
CVPR Best Paper Award, 2009
Outstanding Reviewer: CVPR 2015, ICCV 2015, CVPR 2017
Microsoft Research Asia Fellowship, 2009
Microsoft Research Asia Young Fellowship, 2006
检查清单
站点信息
预览页面
http://kaiminghe.com/