Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Anurag Arnab

PolyViT: Co-training Vision Transformers on Images, Videos and Audio


Nov 25, 2021
Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, Mostafa Dehghani


  Access Paper or Ask Questions

The Efficiency Misnomer


Oct 25, 2021
Mostafa Dehghani, Anurag Arnab, Lucas Beyer, Ashish Vaswani, Yi Tay


  Access Paper or Ask Questions

SCENIC: A JAX Library for Computer Vision Research and Beyond


Oct 18, 2021
Mostafa Dehghani, Alexey Gritsenko, Anurag Arnab, Matthias Minderer, Yi Tay


  Access Paper or Ask Questions

Compressive Visual Representations


Sep 29, 2021
Kuang-Huei Lee, Anurag Arnab, Sergio Guadarrama, John Canny, Ian Fischer

* 27 pages, 4 figures, to appear at NeurIPS 2021 

  Access Paper or Ask Questions

Attention Bottlenecks for Multimodal Fusion


Jun 30, 2021
Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, Chen Sun


  Access Paper or Ask Questions

TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?


Jun 21, 2021
Michael S. Ryoo, AJ Piergiovanni, Anurag Arnab, Mostafa Dehghani, Anelia Angelova


  Access Paper or Ask Questions

ViViT: A Video Vision Transformer


Mar 29, 2021
Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, Cordelia Schmid


  Access Paper or Ask Questions

Unified Graph Structured Models for Video Understanding


Mar 29, 2021
Anurag Arnab, Chen Sun, Cordelia Schmid


  Access Paper or Ask Questions

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos


Jul 21, 2020
Anurag Arnab, Chen Sun, Arsha Nagrani, Cordelia Schmid

* ECCV 2020 

  Access Paper or Ask Questions

Dual Graph Convolutional Network for Semantic Segmentation


Sep 13, 2019
Li Zhang, Xiangtai Li, Anurag Arnab, Kuiyuan Yang, Yunhai Tong, Philip H. S. Torr

* accepted at BMVC 2019 

  Access Paper or Ask Questions

Dynamic Graph Message Passing Networks


Aug 19, 2019
Li Zhang, Dan Xu, Anurag Arnab, Philip H. S. Torr


  Access Paper or Ask Questions

Exploiting temporal context for 3D human pose estimation in the wild


May 10, 2019
Anurag Arnab, Carl Doersch, Andrew Zisserman

* CVPR 2019 

  Access Paper or Ask Questions

Weakly- and Semi-Supervised Panoptic Segmentation


Aug 10, 2018
Qizhu Li, Anurag Arnab, Philip H. S Torr

* ECCV 2018. The first two authors contributed equally 

  Access Paper or Ask Questions

On the Robustness of Semantic Segmentation Models to Adversarial Attacks


Jul 08, 2018
Anurag Arnab, Ondrej Miksik, Philip H. S. Torr

* CVPR 2018 extended version 

  Access Paper or Ask Questions

A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials


Jan 02, 2018
Måns Larsson, Anurag Arnab, Fredrik Kahl, Shuai Zheng, Philip Torr

* Presented at EMMCVPR 2017 conference 

  Access Paper or Ask Questions

Holistic, Instance-Level Human Parsing


Sep 11, 2017
Qizhu Li, Anurag Arnab, Philip H. S. Torr

* Poster at BMVC 2017 

  Access Paper or Ask Questions

Pixelwise Instance Segmentation with a Dynamically Instantiated Network


Apr 07, 2017
Anurag Arnab, Philip H. S Torr

* CVPR 2017 

  Access Paper or Ask Questions

Bottom-up Instance Segmentation using Deep Higher-Order CRFs


Sep 08, 2016
Anurag Arnab, Philip H. S. Torr

* British Machine Vision Conference (BMVC) 2016 

  Access Paper or Ask Questions

Higher Order Conditional Random Fields in Deep Neural Networks


Jul 29, 2016
Anurag Arnab, Sadeep Jayasumana, Shuai Zheng, Philip Torr

* ECCV 2016 

  Access Paper or Ask Questions

Joint Object-Material Category Segmentation from Audio-Visual Cues


Jan 10, 2016
Anurag Arnab, Michael Sapienza, Stuart Golodetz, Julien Valentin, Ondrej Miksik, Shahram Izadi, Philip Torr

* Published in British Machine Vision Conference (BMVC) 2015 

  Access Paper or Ask Questions

SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes


Oct 13, 2015
Stuart Golodetz, Michael Sapienza, Julien P. C. Valentin, Vibhav Vineet, Ming-Ming Cheng, Anurag Arnab, Victor A. Prisacariu, Olaf Kähler, Carl Yuheng Ren, David W. Murray, Shahram Izadi, Philip H. S. Torr

* 33 pages, Project: http://www.semantic-paint.com, Code: https://github.com/torrvision/spaint 

  Access Paper or Ask Questions