[TPAMI'24] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

Implementation of Baseline for Scene Text-to-Scene Text Translation

Comprehensive Scene Text Recognition Toolkit across 13 Indian Languages

Large-Scale Scene Text Dataset for 13 Indic Languages

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding b…

Official Implementation of our EMLNP 2024 Paper

Official inference framework for 1-bit LLMs

OCR Tamil is a powerful tool that can detect and recognize text in Tamil images with high accuracy on Natural Scenes

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Repo to host the forms dataset

AI algorithms

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

This repository is to prepare for Machine Learning interviews.

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

An awesome README template to jumpstart your projects!

pix2tex: Using a ViT to convert images of equations into LaTeX code.

Utilize OpenCV and ROS Humble to create a ROS node that communicates with an ESP32 over WiFi. This project detects hand gestures, publishing to a Micro-ROS topic to control an LED—illuminate on ope…

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Simple android weather application

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

An easy way to extract information from documents

Using Pytorch Deep Learning Framework to classify if image is checked-checkbox, unchecked-checkbox, or others with triplet loss

This uses Hugging Face Spaces powered by Gradio API to create a simple html page

This repo contains code to convert Structured Documents to Graphs and implement a Graph Convolution Neural Network for node classification

A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character/word embeddings