projects

mwTokenizer

python pyspark nlp tokenization wikipedia multilingual

Python library for multilingual tokenization done for the Wikimedia Foundation.

VISTA for Automated Retail Check-out

python segmentation computer-vision object-detection real-time cross-domain

Official implementation of the VISTA algorithm for automated retail check-out.

mwparserfromhtml

python html metadata parsing mining

A python library for parsing and mining metadata from the Enterprise HTML Dumps.

Comparative Analysis of DL methods for Multi-domain Medical Image Segmentation

python computer-vision machine-learning medical-imaging transfer-learning deep-learning

How do statistical methods, Transformers, zero-shot learning strategies, few-shot finetuning, and low-rank adaptation techniques compare in terms of accuracy and robustness across different medical imaging datasets?

Comparative Analysis of DL methods for Multi-domain Medical Image Segmentation

Rule-based hand gesture recognition

Python Computer Vision Image Processing OpenCV

Implementation of a image processing pipeline that takes input image stream from the webcam, performs a series of classical image processing operations to identify the object of interest, and then displays the processed image with the object of interest highlighted on a GUI.

Git Commit Generation from large GitDiff

NLP Text Generation Text Summarization Git Commit Generation LSTM Transformer BERT GPT-2 Zero-shot learning

Replication and evaluation of standard architectures used for text summarization and generation across varying architectural complexities - e.g, RNN, LSTM, GRU, Transformer, BERT, GPT-2, Zero-shot learning, etc.