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 Vishal M. Patel

Vishal M. Patel

Adversarially Robust One-class Novelty Detection


Aug 25, 2021
Shao-Yuan Lo, Poojan Oza, Vishal M. Patel

Figure 1 for Adversarially Robust One-class Novelty Detection
Figure 2 for Adversarially Robust One-class Novelty Detection
Figure 3 for Adversarially Robust One-class Novelty Detection
Figure 4 for Adversarially Robust One-class Novelty Detection

  Access Paper or Ask Questions

A Synthesis-Based Approach for Thermal-to-Visible Face Verification


Aug 21, 2021
Neehar Peri, Joshua Gleason, Carlos D. Castillo, Thirimachos Bourlai, Vishal M. Patel, Rama Chellappa

Figure 1 for A Synthesis-Based Approach for Thermal-to-Visible Face Verification
Figure 2 for A Synthesis-Based Approach for Thermal-to-Visible Face Verification
Figure 3 for A Synthesis-Based Approach for Thermal-to-Visible Face Verification
Figure 4 for A Synthesis-Based Approach for Thermal-to-Visible Face Verification

  Access Paper or Ask Questions

Image Fusion Transformer


Aug 05, 2021
Vibashan VS, Jeya Maria Jose Valanarasu, Poojan Oza, Vishal M. Patel

Figure 1 for Image Fusion Transformer
Figure 2 for Image Fusion Transformer
Figure 3 for Image Fusion Transformer
Figure 4 for Image Fusion Transformer

  Access Paper or Ask Questions

Heterogeneous Face Frontalization via Domain Agnostic Learning


Jul 17, 2021
Xing Di, Shuowen Hu, Vishal M. Patel

Figure 1 for Heterogeneous Face Frontalization via Domain Agnostic Learning
Figure 2 for Heterogeneous Face Frontalization via Domain Agnostic Learning
Figure 3 for Heterogeneous Face Frontalization via Domain Agnostic Learning
Figure 4 for Heterogeneous Face Frontalization via Domain Agnostic Learning
* This work is accepted in IEEE conference on Automatic Face and Gesture Recognition 2021 (FG2021) 
  Access Paper or Ask Questions

Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection


Jul 14, 2021
Velat Kilic, Deepti Hegde, Vishwanath Sindagi, A. Brinton Cooper, Mark A. Foster, Vishal M. Patel

Figure 1 for Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection
Figure 2 for Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection
Figure 3 for Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection
Figure 4 for Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection

  Access Paper or Ask Questions

Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction


Jul 06, 2021
Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel

Figure 1 for Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
Figure 2 for Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
Figure 3 for Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
Figure 4 for Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction

  Access Paper or Ask Questions

Over-and-Under Complete Convolutional RNN for MRI Reconstruction


Jun 25, 2021
Pengfei Guo, Jeya Maria Jose Valanarasu, Puyang Wang, Jinyuan Zhou, Shanshan Jiang, Vishal M. Patel

Figure 1 for Over-and-Under Complete Convolutional RNN for MRI Reconstruction
Figure 2 for Over-and-Under Complete Convolutional RNN for MRI Reconstruction
Figure 3 for Over-and-Under Complete Convolutional RNN for MRI Reconstruction
Figure 4 for Over-and-Under Complete Convolutional RNN for MRI Reconstruction
* Accepted to MICCAI 2021 
  Access Paper or Ask Questions

Unsupervised Domain Adaption of Object Detectors: A Survey


May 27, 2021
Poojan Oza, Vishwanath A. Sindagi, Vibashan VS, Vishal M. Patel

Figure 1 for Unsupervised Domain Adaption of Object Detectors: A Survey
Figure 2 for Unsupervised Domain Adaption of Object Detectors: A Survey
Figure 3 for Unsupervised Domain Adaption of Object Detectors: A Survey
Figure 4 for Unsupervised Domain Adaption of Object Detectors: A Survey

  Access Paper or Ask Questions

Federated Learning-based Active Authentication on Mobile Devices


Apr 14, 2021
Poojan Oza, Vishal M. Patel

Figure 1 for Federated Learning-based Active Authentication on Mobile Devices
Figure 2 for Federated Learning-based Active Authentication on Mobile Devices
Figure 3 for Federated Learning-based Active Authentication on Mobile Devices
Figure 4 for Federated Learning-based Active Authentication on Mobile Devices

  Access Paper or Ask Questions

Federated Generalized Face Presentation Attack Detection


Apr 14, 2021
Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

Figure 1 for Federated Generalized Face Presentation Attack Detection
Figure 2 for Federated Generalized Face Presentation Attack Detection
Figure 3 for Federated Generalized Face Presentation Attack Detection
Figure 4 for Federated Generalized Face Presentation Attack Detection
* arXiv admin note: substantial text overlap with arXiv:2005.14638 
  Access Paper or Ask Questions

Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN


Apr 13, 2021
Rakhil Immidisetti, Shuowen Hu, Vishal M. Patel

Figure 1 for Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
Figure 2 for Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
Figure 3 for Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
Figure 4 for Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN

  Access Paper or Ask Questions

Multimodal Face Synthesis from Visual Attributes


Apr 09, 2021
Xing Di, Vishal M. Patel

Figure 1 for Multimodal Face Synthesis from Visual Attributes
Figure 2 for Multimodal Face Synthesis from Visual Attributes
Figure 3 for Multimodal Face Synthesis from Visual Attributes
Figure 4 for Multimodal Face Synthesis from Visual Attributes
* IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM) submission 
  Access Paper or Ask Questions

MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection


Apr 03, 2021
Vibashan VS, Vikram Gupta, Poojan Oza, Vishwanath A. Sindagi, Vishal M. Patel

Figure 1 for MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Figure 2 for MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Figure 3 for MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Figure 4 for MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
* Accepted to CVPR 2021 
  Access Paper or Ask Questions

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning


Mar 10, 2021
Pengfei Guo, Puyang Wang, Jinyuan Zhou, Shanshan Jiang, Vishal M. Patel

Figure 1 for Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
Figure 2 for Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
Figure 3 for Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
Figure 4 for Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
* Accepted at CVPR 2021 
  Access Paper or Ask Questions

Multi-Feature Multi-Scale CNN-Derived COVID-19 Classification from Lung Ultrasound Data


Feb 23, 2021
Hui Che, Jared Radbel, Jag Sunderram, John L. Nosher, Vishal M. Patel, Ilker Hacihaliloglu

Figure 1 for Multi-Feature Multi-Scale CNN-Derived COVID-19 Classification from Lung Ultrasound Data
Figure 2 for Multi-Feature Multi-Scale CNN-Derived COVID-19 Classification from Lung Ultrasound Data
Figure 3 for Multi-Feature Multi-Scale CNN-Derived COVID-19 Classification from Lung Ultrasound Data

  Access Paper or Ask Questions

Medical Transformer: Gated Axial-Attention for Medical Image Segmentation


Feb 21, 2021
Jeya Maria Jose Valanarasu, Poojan Oza, Ilker Hacihaliloglu, Vishal M. Patel

Figure 1 for Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
Figure 2 for Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
Figure 3 for Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
Figure 4 for Medical Transformer: Gated Axial-Attention for Medical Image Segmentation

  Access Paper or Ask Questions

Error Diffusion Halftoning Against Adversarial Examples


Jan 23, 2021
Shao-Yuan Lo, Vishal M. Patel

Figure 1 for Error Diffusion Halftoning Against Adversarial Examples
Figure 2 for Error Diffusion Halftoning Against Adversarial Examples
Figure 3 for Error Diffusion Halftoning Against Adversarial Examples
Figure 4 for Error Diffusion Halftoning Against Adversarial Examples

  Access Paper or Ask Questions

One-Class Classification: A Survey


Jan 08, 2021
Pramuditha Perera, Poojan Oza, Vishal M. Patel

Figure 1 for One-Class Classification: A Survey
Figure 2 for One-Class Classification: A Survey
Figure 3 for One-Class Classification: A Survey
Figure 4 for One-Class Classification: A Survey

  Access Paper or Ask Questions

A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset


Jan 07, 2021
Domenick Poster, Matthew Thielke, Robert Nguyen, Srinivasan Rajaraman, Xing Di, Cedric Nimpa Fondje, Vishal M. Patel, Nathaniel J. Short, Benjamin S. Riggan, Nasser M. Nasrabadi, Shuowen Hu

Figure 1 for A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset
Figure 2 for A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset
Figure 3 for A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset
Figure 4 for A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset

  Access Paper or Ask Questions

Overcomplete Representations Against Adversarial Videos


Dec 08, 2020
Shao-Yuan Lo, Jeya Maria Jose Valanarasu, Vishal M. Patel

Figure 1 for Overcomplete Representations Against Adversarial Videos
Figure 2 for Overcomplete Representations Against Adversarial Videos
Figure 3 for Overcomplete Representations Against Adversarial Videos

  Access Paper or Ask Questions

Image Inpainting with Contextual Reconstruction Loss


Nov 25, 2020
Yu Zeng, Zhe Lin, Huchuan Lu, Vishal M. Patel

Figure 1 for Image Inpainting with Contextual Reconstruction Loss
Figure 2 for Image Inpainting with Contextual Reconstruction Loss
Figure 3 for Image Inpainting with Contextual Reconstruction Loss
Figure 4 for Image Inpainting with Contextual Reconstruction Loss

  Access Paper or Ask Questions

Overcomplete Deep Subspace Clustering Networks


Nov 16, 2020
Jeya Maria Jose Valanarasu, Vishal M. Patel

Figure 1 for Overcomplete Deep Subspace Clustering Networks
Figure 2 for Overcomplete Deep Subspace Clustering Networks
Figure 3 for Overcomplete Deep Subspace Clustering Networks
Figure 4 for Overcomplete Deep Subspace Clustering Networks
* WACV 2021 
  Access Paper or Ask Questions

Deep Image Compositing


Nov 04, 2020
He Zhang, Jianming Zhang, Federico Perazzi, Zhe Lin, Vishal M. Patel

Figure 1 for Deep Image Compositing
Figure 2 for Deep Image Compositing
Figure 3 for Deep Image Compositing
Figure 4 for Deep Image Compositing
* WACV-2021. A better portrait segmentation technology has been shipped in Photoshop 2020. Check this out if you are not sure how to use it. https://www.youtube.com/watch?v=v_kitSYKr3s&t=138s 
  Access Paper or Ask Questions