BIO
I am currently working as an Applied Scientist at Amazon Go.
Before this, I completed my PhD in Computer science at University of Maryland, College Park , M.S in Electrical Engineering at Stanford University , M.Tech at IIT Kanpur and B.E at Bengal Engineering and Science University, Shibpur. At Maryland I worked with Professor Larry Davis and Professor Abhinav Shrivastava on a couple of different projects. My research focus was on graph convolution networks for zero/few-shot shot action recognition. At Stanford, I was working with Professor Silvio Savarese, on tiny and indistinct object detection and tracking in a crowd. I have taken courses based on computer vision, image processing, machine learning, databases and statistics.
During the course of my stay in the US for my M.S and Ph.D degrees, I have completed multiple internships, namely Microsoft Research, SRI International, One Concern Inc, Meta Co., and Pantry Labs. All of these experiences helped me in developing a strong base in the fields of Machine Learning and Computer Vision.
Publications
1. Learning Graphs for Knowledge Transfer with Limited Labels
Pallabi Ghosh, Nirat Saini, Larry Davis, Abhinav Shivastava
CVPR 2021
2. Depth Completion Using a View-constrained Deep Prior
Pallabi Ghosh, Vibhav Vineet, Larry S. Davis, Abhinav Shrivastava, Sudipta Sinha, Neel Joshi
3DV 2020
3. Stacked Spatio-Temporal Graph Convolutional Networks for Action
Segmentation
Pallabi Ghosh, Yi Yao, Larry S. Davis, Ajay Divakaran
WACV 2020
4. Understanding Center Loss Based Network for
Image Retrieval with Few Training Data
Pallabi Ghosh, Larry S. Davis
ECCV Workshop 2018
5. Detection of Metadata Tampering Through Discrepancy Between Image Content and Metadata Using Multi-task Deep Learning
Bor-Chun Chen, Pallabi Ghosh, Vlad I. Morariu, Larry S. Davis
CVPR Workshop 2017
6. Multistereo System Design
Apoorva Bhatia, Pallabi Ghosh, K.S. Venkatesh
ICIIP 2013
7. Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
Sohil Shah, Pallabi Ghosh, Larry S Davis, Tom Goldstein
Arxiv
8. All About Knowledge Graphs for Actions
Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava
Arxiv
Other projects
1. Detecting and Tracking ants in their colony
Collaborators: Shabaz Patel and Alexandre Alahi
Develop an algorithm based on neural networks to detect very similar and small objects like ants in extremely crowded environments.
2. Low Resolution Scene Representation for Retinal Prostheses
Collaboraters: Ayesha Khwaja and John Doherty
We generated an information rich representation of the scene that can be output to the retinal implant that displays scene at a low resolution
Overall Algorithm Flow
Labelling results on our datasets
3. Perfect Moments
Collaboraters: Ayesha Khwaja
We took multiple images of a group of people, selected their best faces and replaced these faces in the reference frame to get the perfect picture.
The first two columns show the input images captured, the third column shows the results of homography and pyramid blending, and the last column show the results of template matching
4. Recognizing products inside a fridge
Collaboraters:Maxime Bassenne
We tried to recognize items placed in a fridge using SIFT matching on segmentation results on difference images.
Our Algorithm
5. Analysis of real camera lenses
Collaborators: Ayesha Khwaja, Atinuke Ademola-Idowu
We tried to estimate the PSF of camera lenses and use it to deblur captured images.
6. Dense Stereo Matching Using Machine Learning
Collaboraters: Nattamon Thavornpitak, Ayesha Khwaja
We tried to estimate stereo map using SVM and K-means algorithm and Daisy Features
Results obtained using all techniques mentioned above(pixel location, pixel padding and correlation matching). The top row is the image and groundtruth and the bottom row is disparity value obtained from SVM(left) and K-mean clustering algorithm(right).
Misc
Teaching
Teaching assistant at University of Maryland and IIT Kanpur for courses like Human Computer Interaction, Java Programming for beginners and Computer Vision.
Hobbies
Photography
