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

Senior Member, IEEE

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

* 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


  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

Exploring Overcomplete Representations for Single Image Deraining using CNNs


Oct 20, 2020
Rajeev Yasarla, Jeya Maria Jose Valanarasu, Vishal M. Patel

Figure 1 for Exploring Overcomplete Representations for Single Image Deraining using CNNs
Figure 2 for Exploring Overcomplete Representations for Single Image Deraining using CNNs
Figure 3 for Exploring Overcomplete Representations for Single Image Deraining using CNNs
Figure 4 for Exploring Overcomplete Representations for Single Image Deraining using CNNs

  Access Paper or Ask Questions

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation


Oct 04, 2020
Jeya Maria Jose Valanarasu, Vishwanath A. Sindagi, Ilker Hacihaliloglu, Vishal M. Patel

Figure 1 for KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
Figure 2 for KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
Figure 3 for KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
Figure 4 for KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
* Journal Extension of KiU-Net (MICCAI-2020) 
  Access Paper or Ask Questions

MultAV: Multiplicative Adversarial Videos


Sep 17, 2020
Shao-Yuan Lo, Vishal M. Patel

Figure 1 for MultAV: Multiplicative Adversarial Videos
Figure 2 for MultAV: Multiplicative Adversarial Videos
Figure 3 for MultAV: Multiplicative Adversarial Videos

  Access Paper or Ask Questions

Completely Self-Supervised Crowd Counting via Distribution Matching


Sep 14, 2020
Deepak Babu Sam, Abhinav Agarwalla, Jimmy Joseph, Vishwanath A. Sindagi, R. Venkatesh Babu, Vishal M. Patel

Figure 1 for Completely Self-Supervised Crowd Counting via Distribution Matching
Figure 2 for Completely Self-Supervised Crowd Counting via Distribution Matching
Figure 3 for Completely Self-Supervised Crowd Counting via Distribution Matching
Figure 4 for Completely Self-Supervised Crowd Counting via Distribution Matching

  Access Paper or Ask Questions

Defending Against Multiple and Unforeseen Adversarial Videos


Sep 11, 2020
Shao-Yuan Lo, Vishal M. Patel

Figure 1 for Defending Against Multiple and Unforeseen Adversarial Videos
Figure 2 for Defending Against Multiple and Unforeseen Adversarial Videos
Figure 3 for Defending Against Multiple and Unforeseen Adversarial Videos
Figure 4 for Defending Against Multiple and Unforeseen Adversarial Videos

  Access Paper or Ask Questions

Open-set Adversarial Defense


Sep 02, 2020
Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

Figure 1 for Open-set Adversarial Defense
Figure 2 for Open-set Adversarial Defense
Figure 3 for Open-set Adversarial Defense
Figure 4 for Open-set Adversarial Defense
* Accepted by ECCV 2020 
  Access Paper or Ask Questions

Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas


Aug 06, 2020
Pengfei Guo, Puyang Wang, Rajeev Yasarla, Jinyuan Zhou, Vishal M. Patel, Shanshan Jiang

* Submit to IEEE TMI. arXiv admin note: text overlap with arXiv:2006.14761 
  Access Paper or Ask Questions

Anomaly Detection-Based Unknown Face Presentation Attack Detection


Jul 11, 2020
Yashasvi Baweja, Poojan Oza, Pramuditha Perera, Vishal M. Patel

Figure 1 for Anomaly Detection-Based Unknown Face Presentation Attack Detection
Figure 2 for Anomaly Detection-Based Unknown Face Presentation Attack Detection
Figure 3 for Anomaly Detection-Based Unknown Face Presentation Attack Detection
Figure 4 for Anomaly Detection-Based Unknown Face Presentation Attack Detection

  Access Paper or Ask Questions

Learning to Count in the Crowd from Limited Labeled Data


Jul 08, 2020
Vishwanath A. Sindagi, Rajeev Yasarla, Deepak Sam Babu, R. Venkatesh Babu, Vishal M. Patel

Figure 1 for Learning to Count in the Crowd from Limited Labeled Data
Figure 2 for Learning to Count in the Crowd from Limited Labeled Data
Figure 3 for Learning to Count in the Crowd from Limited Labeled Data
Figure 4 for Learning to Count in the Crowd from Limited Labeled Data
* Accepted at ECCV 2020 
  Access Paper or Ask Questions

Quickest Intruder Detection for Multiple User Active Authentication


Jun 21, 2020
Pramuditha Perera, Julian Fierrez, Vishal M. Patel

Figure 1 for Quickest Intruder Detection for Multiple User Active Authentication
Figure 2 for Quickest Intruder Detection for Multiple User Active Authentication
Figure 3 for Quickest Intruder Detection for Multiple User Active Authentication
Figure 4 for Quickest Intruder Detection for Multiple User Active Authentication
* Accepted for publication in ICIP 2020 
  Access Paper or Ask Questions

KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations


Jun 08, 2020
Jeya Maria Jose, Vishwanath Sindagi, Ilker Hacihaliloglu, Vishal M. Patel

Figure 1 for KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
Figure 2 for KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
Figure 3 for KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
Figure 4 for KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
* Provisionally Accepted at MICCAI 2020 
  Access Paper or Ask Questions

Federated Face Anti-spoofing


May 29, 2020
Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

Figure 1 for Federated Face Anti-spoofing
Figure 2 for Federated Face Anti-spoofing
Figure 3 for Federated Face Anti-spoofing
Figure 4 for Federated Face Anti-spoofing

  Access Paper or Ask Questions

Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis


Apr 20, 2020
Xing Di, Benjamin S. Riggan, Shuowen Hu, Nathaniel J. Short, Vishal M. Patel

Figure 1 for Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
Figure 2 for Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
Figure 3 for Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
Figure 4 for Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
* submitted to IEEE Transactions on Information Forensics and Security (TIFS). arXiv admin note: substantial text overlap with arXiv:1901.00889 
  Access Paper or Ask Questions

JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method


Apr 07, 2020
Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel

Figure 1 for JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
Figure 2 for JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
Figure 3 for JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
Figure 4 for JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
* The dataset can be downloaded from http://www.crowd-counting.com. arXiv admin note: substantial text overlap with arXiv:1910.12384 
  Access Paper or Ask Questions

Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data


Dec 18, 2019
Jeya Maria Jose V., Rajeev Yasarla, Puyang Wang, Ilker Hacihaliloglu, Vishal M. Patel

Figure 1 for Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
Figure 2 for Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
Figure 3 for Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
Figure 4 for Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data

  Access Paper or Ask Questions