Alert button
Picture for Mubarak Shah

Mubarak Shah

Alert button

An Efficient 3D CNN for Action/Object Segmentation in Video

Jul 21, 2019
Rui Hou, Chen Chen, Rahul Sukthankar, Mubarak Shah

Figure 1 for An Efficient 3D CNN for Action/Object Segmentation in Video
Figure 2 for An Efficient 3D CNN for Action/Object Segmentation in Video
Figure 3 for An Efficient 3D CNN for Action/Object Segmentation in Video
Figure 4 for An Efficient 3D CNN for Action/Object Segmentation in Video
Viaarxiv icon

Deep Constrained Dominant Sets for Person Re-identification

Apr 25, 2019
Leulseged Tesfaye Alemu, Mubarak Shah, Marcello Pelillo

Figure 1 for Deep Constrained Dominant Sets for Person Re-identification
Figure 2 for Deep Constrained Dominant Sets for Person Re-identification
Figure 3 for Deep Constrained Dominant Sets for Person Re-identification
Figure 4 for Deep Constrained Dominant Sets for Person Re-identification
Viaarxiv icon

Bridging the Domain Gap for Ground-to-Aerial Image Matching

Apr 24, 2019
Krishna Regmi, Mubarak Shah

Figure 1 for Bridging the Domain Gap for Ground-to-Aerial Image Matching
Figure 2 for Bridging the Domain Gap for Ground-to-Aerial Image Matching
Figure 3 for Bridging the Domain Gap for Ground-to-Aerial Image Matching
Figure 4 for Bridging the Domain Gap for Ground-to-Aerial Image Matching
Viaarxiv icon

Crowd Transformer Network

Apr 04, 2019
Viresh Ranjan, Mubarak Shah, Minh Hoai Nguyen

Figure 1 for Crowd Transformer Network
Figure 2 for Crowd Transformer Network
Figure 3 for Crowd Transformer Network
Figure 4 for Crowd Transformer Network
Viaarxiv icon

EgoReID: Person re-identification in Egocentric Videos Acquired by Mobile Devices with First-Person Point-of-View

Dec 22, 2018
Emrah Basaran, Yonatan Tariku Tesfaye, Mubarak Shah

Figure 1 for EgoReID: Person re-identification in Egocentric Videos Acquired by Mobile Devices with First-Person Point-of-View
Figure 2 for EgoReID: Person re-identification in Egocentric Videos Acquired by Mobile Devices with First-Person Point-of-View
Figure 3 for EgoReID: Person re-identification in Egocentric Videos Acquired by Mobile Devices with First-Person Point-of-View
Figure 4 for EgoReID: Person re-identification in Egocentric Videos Acquired by Mobile Devices with First-Person Point-of-View
Viaarxiv icon

Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries

Dec 02, 2018
Bruce McIntosh, Kevin Duarte, Yogesh S Rawat, Mubarak Shah

Figure 1 for Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
Figure 2 for Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
Figure 3 for Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
Figure 4 for Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
Viaarxiv icon

Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision

Nov 29, 2018
Mohsen Joneidi, Alireza Zaeemzadeh, Nazanin Rahnavard, Mubarak Shah

Figure 1 for Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
Figure 2 for Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
Figure 3 for Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
Figure 4 for Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
Viaarxiv icon

Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning

Nov 29, 2018
Shruti Vyas, Yogesh S Rawat, Mubarak Shah

Figure 1 for Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
Figure 2 for Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
Figure 3 for Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
Figure 4 for Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
Viaarxiv icon

Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention

Nov 28, 2018
Pooya Abolghasemi, Amir Mazaheri, Mubarak Shah, Ladislau Bölöni

Figure 1 for Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
Figure 2 for Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
Figure 3 for Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
Figure 4 for Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
Viaarxiv icon

Unsupervised Meta-Learning For Few-Shot Image and Video Classification

Nov 28, 2018
Siavash Khodadadeh, Ladislau Bölöni, Mubarak Shah

Figure 1 for Unsupervised Meta-Learning For Few-Shot Image and Video Classification
Figure 2 for Unsupervised Meta-Learning For Few-Shot Image and Video Classification
Figure 3 for Unsupervised Meta-Learning For Few-Shot Image and Video Classification
Figure 4 for Unsupervised Meta-Learning For Few-Shot Image and Video Classification
Viaarxiv icon