Veeru Talreja

Brief Intro!

I am a Ph.D. candidate at West Virginia University (WVU), Morgantown, USA. I have worked as a deep learning intern at Signify in Cambridge, MA working on application of artificial intelligence in agriculture. I have also worked as a research intern at Mitsubishi Electric Research Lab (MERL) from Jan. 2020 to May, 2020.

I received my Masters in Electrical Engineering degree from West Virginia University in 2010 and the Bachelors in Electronics and Communication Engineering degree from Osmania University, Hyderabad, India in 2005. From 2010 to 2013 I worked as a Geospatial Software Developer with West Virginia University research corporation.

My research interests include applied machine learning, deep learning, coding theory, multimodal biometric recognition and security, and image retrieval.

Updates

07/2021: Sucessfully defended my PhD dissertation and graduated.

06/2021: Got a job as a Computer Vision Scientist at Kinetica Labs.

12/2020: Sucessfully finished my internship at Signify and ready to go back to school and graduate.

10/2020: One Paper "End-to-End Deep Learning for Phase Noise-Robust Multi-Dimensional Geometric Shaping" accepted at ECOC 2020.

10/2020: Best biometrics student paper award for "PF-cpGAN: Profile to Frontal Coupled GAN for Face Recognition in the Wild" at IJCB 2020.

10/2020: One Paper "Deep Hashing for Secure Multimodal Biometrics." accepted at TIFS.

07/2020: One paper "PF-cpGAN: Profile to Frontal Coupled GAN for Face Recognition in the Wild" accepted at IJCB 2020.

07/2020: One paper "Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval." accepted at T-BIOM.

06/2020: Started internship at Signify.

05/2020: Succesfully finished internship at Mitsubishi Electric Research Lab (MERL).

01/2020: Started internship at Mitsubishi Electric Research Lab (MERL).

10/2019: Best poster award for "Deep Profile-Frontal Face Verification in the Wild" at CITeR Fall 2019 meeting.

06/2019: One paper "Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protection." accepted at BTAS 2019.

06/2019: One paper "Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition." accepted at BTAS 2019.

05/2019: Best poster award for "Deep virtual facial line-up using soft biometrics" at CITeR Spring 2019 meeting.

05/2019: A book chapter "A Framework for Secure Selfie-Based Biometric Authentication in the Cloud." published in Rattani A., Derakhshani R., Ross A. (eds) Selfie Biometrics. Advances in Computer Vision and Pattern Recognition. Springer, Cham..

01/2019: One paper "Learning to Authenticate with Deep Multibiometric Hashing and Neural Network Decoding." accepted at ICC 2019.

09/2018: One paper "Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval." accepted at GlobalSIP 2018.

06/2018: One paper "Facial Attribute Guided Deep Cross-Modal Hashing for Face Image Retrieval." accepted at BIOSIG 2018.

10/2017: One paper "Biometrics-as-a-service: A framework to promote innovative biometric recognition in the cloud." accepted at ICCE 2018.

07/2017: One paper "Multibiometric secure system based on deep learning." accepted at GlobalSIP 2017.

Academics

Link to my full curriculum vitae (pdf format - last updated Feb 2021)

Education

2015-2021	PhD in Electrical Engineering, West Virginia University, Morgantown, WV
2007-2010	Master degree in Electrical Engineering, West Virginia University, Morgantown, WV
2001-2005	Bachelor degree in Electronics and Communication Engineering, Osmania University, Hyderabad, India

Skills

Programming	Python, Matlab, C, C++, C#, JAVA, ASP.Net
Deep Learning Frameworks	Pytorch, Tensorflow, Keras, Caffee,
Web Development	HTML, JavaScript, AJAX
General Softwares	Microsoft Office, LATEX

Experience

Research Intern at Mitsubishi Electric Research Lab, Cambridge, MA

Jan. 2020 - May 2020

Deep Learning Intern at Signify Research, Cambridge, MA

June 2020 - Dec. 2020

Selected Academic Services

Journal Reviewer: TMM, T-BIOM, TII

Conference Reviewer: GLOBECOM' 2019, GLOBECOM' 2020

Publications

Please find below a list of publications (last updated Jan 2021)
PDF versions are provided for individual, noncommercial purposes only.

Veeru Talreja, Toshiaki Koike-Akino, Ye Wang, David Millar, Keisuke Kojima, Kieran Parsons. End-to-End Deep Learning for Phase Noise-Robust Multi-Dimensional Geometric Shaping. European Conference on Optical Communications, Dec. 2020.
Veeru Talreja, Matthew C. Valenti, and Nasser M. Nasrabadi. Deep Hashing for Secure Multimodal Biometrics. IEEE Transactions on Information Forensics and Security, vol. 16, 2021.
Fariborz Taherkhani*, Veeru Talreja*, Jeremy Dawson, Matthew C. Valenti, and Nasser M. Nasrabadi. PF-cpGAN: Profile to Frontal Coupled GAN for Face Recognition in the Wild. Proc. IEEE/IAPR International Joint Conference on Biometrics, Oct. 2020. * Co-first authors
Fariborz Taherkhani*, Veeru Talreja*, Matthew C. Valenti, and Nasser M. Nasrabadi. Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval. IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 2, no. 3, July 2020. * Co-first authors
Veeru Talreja, Matthew C. Valenti, and Nasser M. Nasrabadi. Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protection. Proc. IEEE 10th International Conference on Biometrics Theory, Applications and Systems , Sept. 2019.
Veeru Talreja*, Fariborz Taherkhani* Matthew C. Valenti, and Nasser M. Nasrabadi. Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition. Proc. IEEE International Conference on Biometrics Theory, Applications and Systems , Sept. 2019. * Co-first authors
Veeru Talreja, Terry Ferrett, Matthew C. Valenti, and Arun Ross. A Framework for Secure Selfie-Based Biometric Authentication in the Cloud. Rattani A., Derakhshani R., Ross A. (eds) Selfie Biometrics. Advances in Computer Vision and Pattern Recognition. Springer, Cham.
Veeru Talreja, Sobhan Soleymani, Matthew C. Valenti, and Nasser M. Nasrabadi. Learning to Authenticate with Deep Multibiometric Hashing and Neural Network Decoding. Proc. IEEE International Conference on Communications (ICC), Shanghai, China, May 2019.
Veeru Talreja*, Fariborz Taherkhani*, Matthew C. Valenti, and Nasser M. Nasrabadi. Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval. Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), Nov. 2018. * Co-first authors
Fariborz Taherkhani, Veeru Talreja, Hadi Kazemi, and Nasser M. Nasrabadi. Facial Attribute Guided Deep Cross-Modal Hashing for Face Image Retrieval. Proc. IEEE International Conference of the Biometrics Special Interest Group (BIOSIG), Sept. 2018.
Veeru Talreja, Terry Ferrett, Matthew C. Valenti, and Arun Ross. Biometrics-as-a-service: A framework to promote innovative biometric recognition in the cloud. Proc. IEEE International Conference on Consumer Electronics (ICCE), Jan. 2018.
Veeru Talreja, Matthew C. Valenti, and Nasser M. Nasrabadi. Multibiometric secure system based on deep learning. Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), Nov. 2017.

Projects

Semantic Segmentation using UNet

A semantic segmentation model has been implemented using a famous neural network architecture UNet. In this implementation, the UNet architecture is not totally symmetric (number of encoding blocks equal to decoding blocks) and so, in that way it can also be considered as a Fully Convolutional network (FCN) architecture. (Code).

Profile to Frontal Face Recognition in the Wild

Implemented a generative adversarial network (GAN) model for profile to frontal face recognition in the wild by projecting the profile faces and frontal faces into a common latent space for verification or retrieval (PDF).

Cross-Resolution Face Recognition

Designed and implemented an embedding model for cross-resolution face recognition and attribute prediction based on novel attribute-guided deep coupled learning framework using generative adversarial network (GAN) (PDF).

Deep Virtual Facial Line-up using Soft Biometrics

Implemented a fast image retrieval system using deep cross-modal hashing and error correcting codes for quickly searching over a large gallery of faces based solely on a soft-biometric query (facial attributes) (PDF)(PDF)(PDF).

Deep Hashing for Secure Multimodal Biometrics

Used the concepts of error-correcting codes and deep hashing to develop a multimodal biometric security framework for generating a secure multimodal template from each user’s multiple biometrics (PDF)(PDF)(PDF)(PDF).

Cloud-Based Biometric Service Model for Iris and Ocular Recognition using a Smartphone

Implemented a framework for Biometrics- as-a-Service (BaaS) that performs iris/ocular matching operations in the cloud, while using images captured with smartphones (PDF).