Momentum Contrast for Unsupervised Visual Representation Learning

Kaiming He, Haoqi Fan, Yuxin Wu, +2

Convolutional Neural NetworkImage AnalysisMachine LearningData ScienceMachine Vision +12

SlowFast Networks for Video Recognition

Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, +1

Video RecognitionMachine VisionImage AnalysisVideo AnalysisMachine Learning +12

Improved Baselines with Momentum Contrastive Learning

Xinlei Chen, Haoqi Fan, Ross Girshick, +1

arXiv (Cornell University)

Artificial IntelligenceStructured PredictionEngineeringMachine LearningSequential Learning +17

Momentum Contrast for Unsupervised Visual Representation Learning

Kaiming He, Haoqi Fan, Yuxin Wu, +2

arXiv (Cornell University)

Convolutional Neural NetworkImage AnalysisMachine LearningData ScienceMachine Vision +12

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

Yanghao Li, Chao-Yuan Wu, Haoqi Fan, +4

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

EngineeringFeature DetectionMachine LearningAction Recognition (Computer Vision)Multiscale Vision Transformers +17

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution

Yunpeng Chen, Haoqi Fan, Bing Xu, +5

Masked Feature Prediction for Self-Supervised Visual Pre-Training

Chen Wei, Haoqi Fan, Saining Xie, +3

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Machine VisionImage AnalysisMachine LearningMasked RegionsPattern Recognition +12

Long-Term Feature Banks for Detailed Video Understanding

Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, +3

EngineeringMachine LearningAction Recognition (Movement Science)Action Recognition (Computer Vision)Video Datasets +15

Going Deeper into First-Person Activity Recognition

Minghuang Ma, Haoqi Fan, Kris Kitani

Convolutional Neural NetworkEngineeringMachine LearningHuman Pose EstimationFeature Design +15

Masked Autoencoders As Spatiotemporal Learners

Christoph Feichtenhofer, Haoqi Fan, Yanghao Li, +1

arXiv (Cornell University)