Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
A Survey of Technologies in Internet of Things
Published in IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS), 2014
A categorization of the various technologies used to implement the Internet of Things.
Download here
Flat focus: depth of field analysis for the FlatCam lensless imaging system
Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017
A study of the depth-of-field of coded aperture lensless cameras.
Download here
Face Detection and Verification Using Lensless Cameras
Published in IEEE Transactions on Computational Imaging (TCI), 2018
A pipeline (with detailed evaluation) for performing face detection and verification using thin mask-based lensless cameras. A new large and diverse dataset of lensless face images is also provided.
Download here
Near-Linear-Phase IIR Filters Using Gauss-Newton Optimization
Published in IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), 2019
A method based on Gauss-Newton optimization for designing IIR filters with near-linear phase responses.
Download here
Towards Photorealistic Reconstruction of Highly Multiplexed Lensless Images
Published in IEEE/CVF International Conference on Computer Vision (ICCV), 2019
A deep learning method for reconstructing a high-quality image from a mask-based lensless camera capture.
Download here
CAnOPIC: Pre-Digital Privacy-Enhancing Encodings for Computer Vision
Published in IEEE International Conference on Multimedia and Expo (ICME), 2020
A proposed design of a privacy-preserving sensor for machine learning tasks built by adding carefully chosen optical and analog components to a conventional imaging sensor.
Download here
Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels
Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Using the recurrent neural tangent kernel to perform kernel-based dimensionality reduction on variable-length signals/sequences
Download here
EDoF-ToF: extended depth of field time-of-flight imaging
Published in Optica Optics Express, 2021
A method for extending the depth-of-field of large-aperture time-of-flight cameras with the help of a proposed efficient large-aperture time-of-flight simulator.
Download here
MINER: Multiscale Implicit Neural Representations
Published in European Conference on Computer Vision (ECCV), 2022
A new multi-scale method for implicit neural representations based on residual learning and Laplacian pyramids resulting in high accuracy with very short training times.
Download here
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference
Published in Neural Information Processing Systems (NeurIPS), 2022
Theoretical and empirical evidence showing how increasing the parameters of a regression model increases its vulnerability to membership inference attacks for various data settings.
Download here
A blessing of dimensionality in membership inference through regularization
Published in AISTATS, 2023
Study of how regularization can lead to larger models having both improved privacy and performance than their smaller counterparts.
Download here
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.