Christoph Feichtenhofer

Research Scientist

I am a research scientist at Facebook AI Research (FAIR). Prior to joining Facebook in Spring 2018, I received the PhD degree in computer science from TU Graz, and spent time as a visiting researcher at the York University Toronto and the University of Oxford. I am the recipient of a DOC Fellowship of the Austrian Academy of Sciences and my PhD thesis was awarded with the Award of Excellence for outstanding doctoral theses in Austria. My main areas of research include the development of effective representations for video understanding. I aim to find solutions for problems that are grounded in applications such as recognition and detection from video.


Computer vision and deep learning

Latest Publications

International Conference on Computer Vision (ICCV) - October 11, 2021

Multiview Pseudo-Labeling for Semi-supervised Learning from Video

Bo Xiong, Haoqi Fan, Kristen Grauman, Christoph Feichtenhofer

CVPR - June 16, 2020

A Multigrid Method for Efficiently Training Video Models

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

CVPR - June 14, 2020

EGO-TOPO: Environment Affordances from Egocentric Video

Tushar Nagarajan, Yanghao Li, Christoph Feichtenhofer, Kristen Grauman

CVPR - June 9, 2020

X3D: Expanding Architectures for Efficient Video Recognition

Christoph Feichtenhofer

ICCV - October 28, 2019

SlowFast Networks for Video Recognition

Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He

NeurIPS - October 27, 2019

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Gedas Bertasius, Christoph Feichtenhofer, Du Tran, Jianbo Shi, Lorenzo Torresani

ICCV - October 26, 2019

Grounded Human-Object Interaction Hotspots From Video

Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman

CVPR - June 18, 2019

Long-Term Feature Banks for Detailed Video Understanding

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

CVPR - June 16, 2019

3D human pose estimation in video with temporal convolutions and semi-supervised training

Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli