Alert button
Picture for Roozbeh Mottaghi

Roozbeh Mottaghi

Alert button

SeGAN: Segmenting and Generating the Invisible

May 07, 2018
Kiana Ehsani, Roozbeh Mottaghi, Ali Farhadi

Figure 1 for SeGAN: Segmenting and Generating the Invisible
Figure 2 for SeGAN: Segmenting and Generating the Invisible
Figure 3 for SeGAN: Segmenting and Generating the Invisible
Figure 4 for SeGAN: Segmenting and Generating the Invisible
Viaarxiv icon

AI2-THOR: An Interactive 3D Environment for Visual AI

Dec 14, 2017
Eric Kolve, Roozbeh Mottaghi, Daniel Gordon, Yuke Zhu, Abhinav Gupta, Ali Farhadi

Figure 1 for AI2-THOR: An Interactive 3D Environment for Visual AI
Figure 2 for AI2-THOR: An Interactive 3D Environment for Visual AI
Figure 3 for AI2-THOR: An Interactive 3D Environment for Visual AI
Figure 4 for AI2-THOR: An Interactive 3D Environment for Visual AI
Viaarxiv icon

See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content

Sep 06, 2017
Roozbeh Mottaghi, Connor Schenck, Dieter Fox, Ali Farhadi

Figure 1 for See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content
Figure 2 for See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content
Figure 3 for See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content
Figure 4 for See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content
Viaarxiv icon

Visual Semantic Planning using Deep Successor Representations

Aug 15, 2017
Yuke Zhu, Daniel Gordon, Eric Kolve, Dieter Fox, Li Fei-Fei, Abhinav Gupta, Roozbeh Mottaghi, Ali Farhadi

Figure 1 for Visual Semantic Planning using Deep Successor Representations
Figure 2 for Visual Semantic Planning using Deep Successor Representations
Figure 3 for Visual Semantic Planning using Deep Successor Representations
Figure 4 for Visual Semantic Planning using Deep Successor Representations
Viaarxiv icon

Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning

Sep 16, 2016
Yuke Zhu, Roozbeh Mottaghi, Eric Kolve, Joseph J. Lim, Abhinav Gupta, Li Fei-Fei, Ali Farhadi

Figure 1 for Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
Figure 2 for Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
Figure 3 for Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
Figure 4 for Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
Viaarxiv icon

"What happens if..." Learning to Predict the Effect of Forces in Images

Mar 17, 2016
Roozbeh Mottaghi, Mohammad Rastegari, Abhinav Gupta, Ali Farhadi

Figure 1 for "What happens if..." Learning to Predict the Effect of Forces in Images
Figure 2 for "What happens if..." Learning to Predict the Effect of Forces in Images
Figure 3 for "What happens if..." Learning to Predict the Effect of Forces in Images
Figure 4 for "What happens if..." Learning to Predict the Effect of Forces in Images
Viaarxiv icon

Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images

Nov 12, 2015
Roozbeh Mottaghi, Hessam Bagherinezhad, Mohammad Rastegari, Ali Farhadi

Figure 1 for Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
Figure 2 for Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
Figure 3 for Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
Figure 4 for Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
Viaarxiv icon

A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition

Apr 10, 2015
Roozbeh Mottaghi, Yu Xiang, Silvio Savarese

Figure 1 for A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition
Figure 2 for A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition
Figure 3 for A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition
Figure 4 for A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition
Viaarxiv icon

Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding

Jun 16, 2014
Roozbeh Mottaghi, Sanja Fidler, Alan Yuille, Raquel Urtasun, Devi Parikh

Figure 1 for Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding
Figure 2 for Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding
Figure 3 for Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding
Figure 4 for Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding
Viaarxiv icon

Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts

Jun 08, 2014
Xianjie Chen, Roozbeh Mottaghi, Xiaobai Liu, Sanja Fidler, Raquel Urtasun, Alan Yuille

Figure 1 for Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Figure 2 for Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Figure 3 for Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Figure 4 for Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Viaarxiv icon