Alert button
Picture for Abhinav Gupta

Abhinav Gupta

Alert button

The Pose Knows: Video Forecasting by Generating Pose Futures

Apr 28, 2017
Jacob Walker, Kenneth Marino, Abhinav Gupta, Martial Hebert

Figure 1 for The Pose Knows: Video Forecasting by Generating Pose Futures
Figure 2 for The Pose Knows: Video Forecasting by Generating Pose Futures
Figure 3 for The Pose Knows: Video Forecasting by Generating Pose Futures
Figure 4 for The Pose Knows: Video Forecasting by Generating Pose Futures
Viaarxiv icon

Learning to Fly by Crashing

Apr 27, 2017
Dhiraj Gandhi, Lerrel Pinto, Abhinav Gupta

Figure 1 for Learning to Fly by Crashing
Figure 2 for Learning to Fly by Crashing
Figure 3 for Learning to Fly by Crashing
Figure 4 for Learning to Fly by Crashing
Viaarxiv icon

The More You Know: Using Knowledge Graphs for Image Classification

Apr 22, 2017
Kenneth Marino, Ruslan Salakhutdinov, Abhinav Gupta

Figure 1 for The More You Know: Using Knowledge Graphs for Image Classification
Figure 2 for The More You Know: Using Knowledge Graphs for Image Classification
Figure 3 for The More You Know: Using Knowledge Graphs for Image Classification
Figure 4 for The More You Know: Using Knowledge Graphs for Image Classification
Viaarxiv icon

Spatial Memory for Context Reasoning in Object Detection

Apr 13, 2017
Xinlei Chen, Abhinav Gupta

Figure 1 for Spatial Memory for Context Reasoning in Object Detection
Figure 2 for Spatial Memory for Context Reasoning in Object Detection
Figure 3 for Spatial Memory for Context Reasoning in Object Detection
Figure 4 for Spatial Memory for Context Reasoning in Object Detection
Viaarxiv icon

What's in a Question: Using Visual Questions as a Form of Supervision

Apr 12, 2017
Siddha Ganju, Olga Russakovsky, Abhinav Gupta

Figure 1 for What's in a Question: Using Visual Questions as a Form of Supervision
Figure 2 for What's in a Question: Using Visual Questions as a Form of Supervision
Figure 3 for What's in a Question: Using Visual Questions as a Form of Supervision
Figure 4 for What's in a Question: Using Visual Questions as a Form of Supervision
Viaarxiv icon

A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

Apr 11, 2017
Xiaolong Wang, Abhinav Shrivastava, Abhinav Gupta

Figure 1 for A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
Figure 2 for A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
Figure 3 for A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
Figure 4 for A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
Viaarxiv icon

ActionVLAD: Learning spatio-temporal aggregation for action classification

Apr 10, 2017
Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic, Bryan Russell

Figure 1 for ActionVLAD: Learning spatio-temporal aggregation for action classification
Figure 2 for ActionVLAD: Learning spatio-temporal aggregation for action classification
Figure 3 for ActionVLAD: Learning spatio-temporal aggregation for action classification
Figure 4 for ActionVLAD: Learning spatio-temporal aggregation for action classification
Viaarxiv icon

Learning From Noisy Large-Scale Datasets With Minimal Supervision

Apr 10, 2017
Andreas Veit, Neil Alldrin, Gal Chechik, Ivan Krasin, Abhinav Gupta, Serge Belongie

Figure 1 for Learning From Noisy Large-Scale Datasets With Minimal Supervision
Figure 2 for Learning From Noisy Large-Scale Datasets With Minimal Supervision
Figure 3 for Learning From Noisy Large-Scale Datasets With Minimal Supervision
Figure 4 for Learning From Noisy Large-Scale Datasets With Minimal Supervision
Viaarxiv icon

Robust Adversarial Reinforcement Learning

Mar 08, 2017
Lerrel Pinto, James Davidson, Rahul Sukthankar, Abhinav Gupta

Figure 1 for Robust Adversarial Reinforcement Learning
Figure 2 for Robust Adversarial Reinforcement Learning
Figure 3 for Robust Adversarial Reinforcement Learning
Figure 4 for Robust Adversarial Reinforcement Learning
Viaarxiv icon

PixelNet: Representation of the pixels, by the pixels, and for the pixels

Feb 21, 2017
Aayush Bansal, Xinlei Chen, Bryan Russell, Abhinav Gupta, Deva Ramanan

Figure 1 for PixelNet: Representation of the pixels, by the pixels, and for the pixels
Figure 2 for PixelNet: Representation of the pixels, by the pixels, and for the pixels
Figure 3 for PixelNet: Representation of the pixels, by the pixels, and for the pixels
Figure 4 for PixelNet: Representation of the pixels, by the pixels, and for the pixels
Viaarxiv icon