|
I am a Sr. Research Engineer at Apple. I am currently focusing on image and video understanding with the goal to provide the best on-device human experiences! Prior to Apple, I was a Sr. Research Scientist at Clarifai working on building a computer vision platform and an Applied Scientist at Vidado.ai working in document image analysis. Before Clarifai and Vidado, I was a Research Scientist at SONY US Research Center where I worked on semantic segmentation for limited resource computing devices. I received my Ph.D. in EECS from Northwestern University in 2016 where I worked under the supervision of Aggelos K. Katsaggelos in the Image and Video Laboratory (IVPL). Email / Resume / Thesis / Google Scholar / LinkedIn |
|
2022 - Present 
2020 - 2022 
2017 - 2020 
2016 - 2017 |
|
My research has been focused in video compressive sensing for perceived quality video reconstruction and recognition. The methodologies and techniques I have applied include sparsity-seeking optimization and deep learning based models. My current research goal is to understand human-objects relations in images and videos and building efficient on-device representations. Relevant tasks I have worked on recently include object detection, human pose estimation and vision-language models. |
 |
We propose a novel encoder-decoder neural network model called DeepBinaryMask for video compressive sensing. The proposed framework is an end-to-end model where the sensing matrix is trained along with the video reconstruction. |
 |
We review the popular neural network architectures used for imaging tasks, offering some insight as to how these deep-learning tools can solve the inverse problem. |
 |
A deep learning framework for video compressive sensing. |
 |
A fast iterative method to address the face identification problem with block occlusions. |
 |
The proposed formulation allows the simultaneous use of various loss functions for modeling the residual in face images. |
 |
We propose a fast, robust and memory efficient video sequence alignment algorithm which has linear space and time complexity. |
 |
Effectively, our method combines the sparsity-based approaches with additional least-squares steps. |
 |
A content based image retrieval application for searching landmarks and buildings in a city using a smartphone. |
 |
The approach takes advantage of Multiple Measurement Vectors (MMV), seeking for significantly sparser solutions, assuming that the solution vectors have similar sparsity structure. |
|
|
 |
|
|
I copied the source code of this website from here. |