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 Sanja Fidler

Sanja Fidler

Personalized Federated Learning with First Order Model Optimization


Jan 28, 2021
Michael Zhang, Karan Sapra, Sanja Fidler, Serena Yeung, Jose M. Alvarez

Figure 1 for Personalized Federated Learning with First Order Model Optimization
Figure 2 for Personalized Federated Learning with First Order Model Optimization
Figure 3 for Personalized Federated Learning with First Order Model Optimization
Figure 4 for Personalized Federated Learning with First Order Model Optimization
* ICLR 2021 
  Access Paper or Ask Questions

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes


Jan 26, 2021
Towaki Takikawa, Joey Litalien, Kangxue Yin, Karsten Kreis, Charles Loop, Derek Nowrouzezahrai, Alec Jacobson, Morgan McGuire, Sanja Fidler

Figure 1 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Figure 2 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Figure 3 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Figure 4 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

  Access Paper or Ask Questions

UniCon: Universal Neural Controller For Physics-based Character Motion


Nov 30, 2020
Tingwu Wang, Yunrong Guo, Maria Shugrina, Sanja Fidler

Figure 1 for UniCon: Universal Neural Controller For Physics-based Character Motion
Figure 2 for UniCon: Universal Neural Controller For Physics-based Character Motion
Figure 3 for UniCon: Universal Neural Controller For Physics-based Character Motion
Figure 4 for UniCon: Universal Neural Controller For Physics-based Character Motion
* 15 pages, 15 figures 
  Access Paper or Ask Questions

Emergent Road Rules In Multi-Agent Driving Environments


Nov 21, 2020
Avik Pal, Jonah Philion, Yuan-Hong Liao, Sanja Fidler

Figure 1 for Emergent Road Rules In Multi-Agent Driving Environments
Figure 2 for Emergent Road Rules In Multi-Agent Driving Environments
Figure 3 for Emergent Road Rules In Multi-Agent Driving Environments
Figure 4 for Emergent Road Rules In Multi-Agent Driving Environments
* Project Page: http://fidler-lab.github.io/social-driving 
  Access Paper or Ask Questions

Learning Deformable Tetrahedral Meshes for 3D Reconstruction


Nov 03, 2020
Jun Gao, Wenzheng Chen, Tommy Xiang, Alec Jacobson, Morgan McGuire, Sanja Fidler

Figure 1 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Figure 2 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Figure 3 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Figure 4 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
* Accepted to NeurIPS 2020 
  Access Paper or Ask Questions

The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes


Oct 24, 2020
Yiluan Guo, Holger Caesar, Oscar Beijbom, Jonah Philion, Sanja Fidler

Figure 1 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
Figure 2 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
Figure 3 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
Figure 4 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
* IROS 2020 Workshop on Benchmarking Progress in Autonomous Driving 
  Access Paper or Ask Questions

Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration


Oct 19, 2020
Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Joshua B. Tenenbaum, Sanja Fidler, Antonio Torralba

Figure 1 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 2 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 3 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 4 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

  Access Paper or Ask Questions

Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering


Oct 18, 2020
Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler

Figure 1 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 2 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 3 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 4 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

  Access Paper or Ask Questions

Fed-Sim: Federated Simulation for Medical Imaging


Sep 01, 2020
Daiqing Li, Amlan Kar, Nishant Ravikumar, Alejandro F Frangi, Sanja Fidler

Figure 1 for Fed-Sim: Federated Simulation for Medical Imaging
Figure 2 for Fed-Sim: Federated Simulation for Medical Imaging
Figure 3 for Fed-Sim: Federated Simulation for Medical Imaging
Figure 4 for Fed-Sim: Federated Simulation for Medical Imaging
* MICCAI 2020 (Early Accept) 
  Access Paper or Ask Questions

Expressive Telepresence via Modular Codec Avatars


Aug 26, 2020
Hang Chu, Shugao Ma, Fernando De la Torre, Sanja Fidler, Yaser Sheikh

Figure 1 for Expressive Telepresence via Modular Codec Avatars
Figure 2 for Expressive Telepresence via Modular Codec Avatars
Figure 3 for Expressive Telepresence via Modular Codec Avatars
Figure 4 for Expressive Telepresence via Modular Codec Avatars
* ECCV 2020 
  Access Paper or Ask Questions

Interactive Annotation of 3D Object Geometry using 2D Scribbles


Aug 24, 2020
Tianchang Shen, Jun Gao, Amlan Kar, Sanja Fidler

Figure 1 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
Figure 2 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
Figure 3 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
Figure 4 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
* Accepted to ECCV 2020 
  Access Paper or Ask Questions

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation


Aug 22, 2020
Bowen Chen, Huan Ling, Xiaohui Zeng, Gao Jun, Ziyue Xu, Sanja Fidler

Figure 1 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
Figure 2 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
Figure 3 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
Figure 4 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

  Access Paper or Ask Questions

Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid


Aug 21, 2020
Jun Gao, Zian Wang, Jinchen Xuan, Sanja Fidler

Figure 1 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
Figure 2 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
Figure 3 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
Figure 4 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
* ECCV 2020 
  Access Paper or Ask Questions

Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation


Aug 20, 2020
Jeevan Devaranjan, Amlan Kar, Sanja Fidler

Figure 1 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Figure 2 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Figure 3 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Figure 4 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
* ECCV 2020 
  Access Paper or Ask Questions

Learning to Generate Diverse Dance Motions with Transformer


Aug 18, 2020
Jiaman Li, Yihang Yin, Hang Chu, Yi Zhou, Tingwu Wang, Sanja Fidler, Hao Li

Figure 1 for Learning to Generate Diverse Dance Motions with Transformer
Figure 2 for Learning to Generate Diverse Dance Motions with Transformer
Figure 3 for Learning to Generate Diverse Dance Motions with Transformer
Figure 4 for Learning to Generate Diverse Dance Motions with Transformer

  Access Paper or Ask Questions

Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D


Aug 13, 2020
Jonah Philion, Sanja Fidler

Figure 1 for Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
Figure 2 for Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
Figure 3 for Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
Figure 4 for Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
* ECCV 2020 
  Access Paper or Ask Questions

Learning to Simulate Dynamic Environments with GameGAN


May 25, 2020
Seung Wook Kim, Yuhao Zhou, Jonah Philion, Antonio Torralba, Sanja Fidler

Figure 1 for Learning to Simulate Dynamic Environments with GameGAN
Figure 2 for Learning to Simulate Dynamic Environments with GameGAN
Figure 3 for Learning to Simulate Dynamic Environments with GameGAN
Figure 4 for Learning to Simulate Dynamic Environments with GameGAN
* CVPR 2020 
  Access Paper or Ask Questions

The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines


Apr 29, 2020
Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray

Figure 1 for The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
Figure 2 for The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
Figure 3 for The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
Figure 4 for The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
* Preprint for paper at IEEE TPAMI. arXiv admin note: substantial text overlap with arXiv:1804.02748 
  Access Paper or Ask Questions

Learning to Evaluate Perception Models Using Planner-Centric Metrics


Apr 19, 2020
Jonah Philion, Amlan Kar, Sanja Fidler

Figure 1 for Learning to Evaluate Perception Models Using Planner-Centric Metrics
Figure 2 for Learning to Evaluate Perception Models Using Planner-Centric Metrics
Figure 3 for Learning to Evaluate Perception Models Using Planner-Centric Metrics
Figure 4 for Learning to Evaluate Perception Models Using Planner-Centric Metrics
* CVPR 2020 poster 
  Access Paper or Ask Questions

Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data


Jan 09, 2020
Xi Yan, David Acuna, Sanja Fidler

Figure 1 for Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data
Figure 2 for Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data
Figure 3 for Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data
Figure 4 for Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data

  Access Paper or Ask Questions

The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries


Jan 01, 2020
Atef Chaudhury, Makarand Tapaswi, Seung Wook Kim, Sanja Fidler

Figure 1 for The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries
Figure 2 for The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries
Figure 3 for The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries
Figure 4 for The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries
* Project page: http://www.cs.toronto.edu/~makarand/shmoop/ Dataset at: https://github.com/achaudhury/shmoop-corpus/ 
  Access Paper or Ask Questions

Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research


Nov 13, 2019
Krishna Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche, Clement Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, Sanja Fidler

Figure 1 for Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
Figure 2 for Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
Figure 3 for Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
Figure 4 for Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
* Kaolin is available as open-source software at https://github.com/NVIDIAGameWorks/kaolin/ 
  Access Paper or Ask Questions

CrevNet: Conditionally Reversible Video Prediction


Oct 25, 2019
Wei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler

Figure 1 for CrevNet: Conditionally Reversible Video Prediction
Figure 2 for CrevNet: Conditionally Reversible Video Prediction

  Access Paper or Ask Questions

Neural Turtle Graphics for Modeling City Road Layouts


Oct 04, 2019
Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, Ming-Yu Liu, Antonio Torralba, Sanja Fidler

Figure 1 for Neural Turtle Graphics for Modeling City Road Layouts
Figure 2 for Neural Turtle Graphics for Modeling City Road Layouts
Figure 3 for Neural Turtle Graphics for Modeling City Road Layouts
Figure 4 for Neural Turtle Graphics for Modeling City Road Layouts
* ICCV-2019 Oral 
  Access Paper or Ask Questions

DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation


Sep 27, 2019
Xiaohui Zeng, Renjie Liao, Li Gu, Yuwen Xiong, Sanja Fidler, Raquel Urtasun

Figure 1 for DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
Figure 2 for DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
Figure 3 for DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
Figure 4 for DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
* ICCV 2019 
  Access Paper or Ask Questions

A Theoretical Analysis of the Number of Shots in Few-Shot Learning


Sep 25, 2019
Tianshi Cao, Marc Law, Sanja Fidler

Figure 1 for A Theoretical Analysis of the Number of Shots in Few-Shot Learning
Figure 2 for A Theoretical Analysis of the Number of Shots in Few-Shot Learning
Figure 3 for A Theoretical Analysis of the Number of Shots in Few-Shot Learning
Figure 4 for A Theoretical Analysis of the Number of Shots in Few-Shot Learning
* 15 pages incl. appendix, 6 figures 
  Access Paper or Ask Questions

Video Face Clustering with Unknown Number of Clusters


Aug 20, 2019
Makarand Tapaswi, Marc T. Law, Sanja Fidler

Figure 1 for Video Face Clustering with Unknown Number of Clusters
Figure 2 for Video Face Clustering with Unknown Number of Clusters
Figure 3 for Video Face Clustering with Unknown Number of Clusters
Figure 4 for Video Face Clustering with Unknown Number of Clusters
* Accepted to ICCV 2019, code and data at https://github.com/makarandtapaswi/BallClustering_ICCV2019 
  Access Paper or Ask Questions