Haoqi Fan

is this you? claim profile

Research Engineer at Facebook AI Research (FAIR), Research Engineer at Carnegie Mellon University’s Robotics Institute

Featured Co-authors

Yi Yang
237 publications
Alan Yuille
161 publications
Jitendra Malik
119 publications
Xiao Wang
102 publications
Kristen Grauman
86 publications
Ross Girshick
65 publications
Meng Li
63 publications
Yuandong Tian
54 publications
Kaiming He
52 publications
Lorenzo Torresani
51 publications
Larry Davis
41 publications

∙ 05/18/2022

Masked Autoencoders As Spatiotemporal Learners

This paper studies a conceptually simple extension of Masked Autoencoder...

Christoph Feichtenhofer, et al. ∙

∙ 04/01/2022

On the Importance of Asymmetry for Siamese Representation Learning

Many recent self-supervised frameworks for visual representation learnin...

Xiao Wang, et al. ∙

∙ 03/29/2022

Unified Transformer Tracker for Object Tracking

As an important area in computer vision, object tracking has formed two ...

Fan Ma, et al. ∙

∙ 01/20/2022

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

While today's video recognition systems parse snapshots or short clips a...

Chao-Yuan Wu, et al. ∙

∙ 12/16/2021

Masked Feature Prediction for Self-Supervised Visual Pre-Training

We present Masked Feature Prediction (MaskFeat) for self-supervised pre-...

Chen Wei, et al. ∙

∙ 12/02/2021

Improved Multiscale Vision Transformers for Classification and Detection

In this paper, we study Multiscale Vision Transformers (MViT) as a unifi...

Yanghao Li, et al. ∙

∙ 11/18/2021

PyTorchVideo: A Deep Learning Library for Video Understanding

We introduce PyTorchVideo, an open-source deep-learning library that pro...

Haoqi Fan, et al. ∙

∙ 04/29/2021

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

We present a large-scale study on unsupervised spatiotemporal representa...

Christoph Feichtenhofer, et al. ∙

∙ 04/22/2021

Multiscale Vision Transformers

We present Multiscale Vision Transformers (MViT) for video and image rec...

Haoqi Fan, et al. ∙

∙ 04/02/2021

Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories

The standard way of training video models entails sampling at each itera...

Xitong Yang, et al. ∙

∙ 04/01/2021

Multiview Pseudo-Labeling for Semi-supervised Learning from Video

We present a multiview pseudo-labeling approach to video learning, a nov...

Bo Xiong, et al. ∙

∙ 03/28/2021

HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval

Video-Text Retrieval has been a hot research topic with the explosion of...

Song Liu, et al. ∙

∙ 11/25/2020

Can Temporal Information Help with Contrastive Self-Supervised Learning?

Leveraging temporal information has been regarded as essential for devel...

Yutong Bai, et al. ∙

∙ 03/09/2020

Improved Baselines with Momentum Contrastive Learning

Contrastive unsupervised learning has recently shown encouraging progres...

Xinlei Chen, et al. ∙

∙ 11/13/2019

Momentum Contrast for Unsupervised Visual Representation Learning

We present Momentum Contrast (MoCo) for unsupervised visual representati...

Kaiming He, et al. ∙

∙ 12/12/2018

Long-Term Feature Banks for Detailed Video Understanding

To understand the world, we humans constantly need to relate the present...

Chao-Yuan Wu, et al. ∙

∙ 12/10/2018

SlowFast Networks for Video Recognition

We present SlowFast networks for video recognition. Our model involves (...

Christoph Feichtenhofer, et al. ∙

∙ 10/06/2017

Efficient K-Shot Learning with Regularized Deep Networks

Feature representations from pre-trained deep neural networks have been ...

Donghyun Yoo, et al. ∙