X3D: Expanding Architectures for Efficient Video Recognition

Apr 09, 2020
Christoph Feichtenhofer

* CVPR 2020 (Oral) 

  Access Model/Code and Paper
Feature Pyramid Grids

Apr 07, 2020
Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin, Christoph Feichtenhofer

* Technical report 

  Access Model/Code and Paper
Audiovisual SlowFast Networks for Video Recognition

Jan 23, 2020
Fanyi Xiao, Yong Jae Lee, Kristen Grauman, Jitendra Malik, Christoph Feichtenhofer

* Technical report 

  Access Model/Code and Paper
EGO-TOPO: Environment Affordances from Egocentric Video

Jan 14, 2020
Tushar Nagarajan, Yanghao Li, Christoph Feichtenhofer, Kristen Grauman


  Access Model/Code and Paper
A Multigrid Method for Efficiently Training Video Models

Dec 02, 2019
Chao-Yuan Wu, Ross Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl

* Technical report 

  Access Model/Code and Paper
Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Jun 06, 2019
Gedas Bertasius, Christoph Feichtenhofer, Du Tran, Jianbo Shi, Lorenzo Torresani

* arXiv admin note: text overlap with arXiv:1812.04172 

  Access Model/Code and Paper
Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)

Jun 03, 2019
Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman

* arXiv admin note: substantial text overlap with arXiv:1812.04558 

  Access Model/Code and Paper
Modeling Human Motion with Quaternion-based Neural Networks

Jan 21, 2019
Dario Pavllo, Christoph Feichtenhofer, Michael Auli, David Grangier

* arXiv admin note: substantial text overlap with arXiv:1805.06485 

  Access Model/Code and Paper
Long-Term Feature Banks for Detailed Video Understanding

Dec 12, 2018
Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick

* Technical report 

  Access Model/Code and Paper
Grounded Human-Object Interaction Hotspots from Video

Dec 11, 2018
Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman


  Access Model/Code and Paper
Learning Discriminative Motion Features Through Detection

Dec 11, 2018
Gedas Bertasius, Christoph Feichtenhofer, Du Tran, Jianbo Shi, Lorenzo Torresani


  Access Model/Code and Paper
SlowFast Networks for Video Recognition

Dec 10, 2018
Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He

* Technical report 

  Access Model/Code and Paper
3D human pose estimation in video with temporal convolutions and semi-supervised training

Nov 28, 2018
Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli

* 13 pages 

  Access Model/Code and Paper
Detect to Track and Track to Detect

Mar 07, 2018
Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman

* ICCV 2017. Code and models: https://github.com/feichtenhofer/Detect-Track Results: https://www.robots.ox.ac.uk/~vgg/research/detect-track/ 

  Access Model/Code and Paper
Camera-based vehicle velocity estimation from monocular video

Feb 20, 2018
Moritz Kampelmühler, Michael G. Müller, Christoph Feichtenhofer

* 8 pages, 5 figures, in CVWW2018 

  Access Model/Code and Paper
What have we learned from deep representations for action recognition?

Jan 04, 2018
Christoph Feichtenhofer, Axel Pinz, Richard P. Wildes, Andrew Zisserman

* This document is best viewed in Adobe Reader where figures play on click. Supplementary material can be downloaded at http://feichtenhofer.github.io/action_vis.pdf 

  Access Model/Code and Paper
Spatiotemporal Residual Networks for Video Action Recognition

Nov 07, 2016
Christoph Feichtenhofer, Axel Pinz, Richard P. Wildes

* NIPS 2016 

  Access Model/Code and Paper
Convolutional Two-Stream Network Fusion for Video Action Recognition

Sep 26, 2016
Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman

* in Proc. CVPR 2016 

  Access Model/Code and Paper