Picture for Amir Ghodrati

Amir Ghodrati

Clockwork Diffusion: Efficient Generation With Model-Step Distillation

Add code
Dec 13, 2023
Viaarxiv icon

Skip-Attention: Improving Vision Transformers by Paying Less Attention

Add code
Jan 17, 2023
Viaarxiv icon

SALISA: Saliency-based Input Sampling for Efficient Video Object Detection

Add code
Apr 05, 2022
Figure 1 for SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
Figure 2 for SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
Figure 3 for SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
Figure 4 for SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
Viaarxiv icon

FrameExit: Conditional Early Exiting for Efficient Video Recognition

Add code
Apr 27, 2021
Figure 1 for FrameExit: Conditional Early Exiting for Efficient Video Recognition
Figure 2 for FrameExit: Conditional Early Exiting for Efficient Video Recognition
Figure 3 for FrameExit: Conditional Early Exiting for Efficient Video Recognition
Figure 4 for FrameExit: Conditional Early Exiting for Efficient Video Recognition
Viaarxiv icon

Video Time: Properties, Encoders and Evaluation

Add code
Jul 18, 2018
Figure 1 for Video Time: Properties, Encoders and Evaluation
Figure 2 for Video Time: Properties, Encoders and Evaluation
Figure 3 for Video Time: Properties, Encoders and Evaluation
Figure 4 for Video Time: Properties, Encoders and Evaluation
Viaarxiv icon

Actor and Action Video Segmentation from a Sentence

Add code
Mar 20, 2018
Figure 1 for Actor and Action Video Segmentation from a Sentence
Figure 2 for Actor and Action Video Segmentation from a Sentence
Figure 3 for Actor and Action Video Segmentation from a Sentence
Figure 4 for Actor and Action Video Segmentation from a Sentence
Viaarxiv icon

Online Action Detection

Add code
Aug 30, 2016
Figure 1 for Online Action Detection
Figure 2 for Online Action Detection
Figure 3 for Online Action Detection
Figure 4 for Online Action Detection
Viaarxiv icon

DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers

Add code
Jun 15, 2016
Figure 1 for DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers
Figure 2 for DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers
Figure 3 for DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers
Figure 4 for DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers
Viaarxiv icon

Rank Pooling for Action Recognition

Add code
May 16, 2016
Figure 1 for Rank Pooling for Action Recognition
Figure 2 for Rank Pooling for Action Recognition
Figure 3 for Rank Pooling for Action Recognition
Figure 4 for Rank Pooling for Action Recognition
Viaarxiv icon

Towards Automatic Image Editing: Learning to See another You

Add code
Nov 26, 2015
Figure 1 for Towards Automatic Image Editing: Learning to See another You
Figure 2 for Towards Automatic Image Editing: Learning to See another You
Figure 3 for Towards Automatic Image Editing: Learning to See another You
Figure 4 for Towards Automatic Image Editing: Learning to See another You
Viaarxiv icon