activity
20142025
most citedScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images

11 citations · 34 across the 12 of their papers we have counts for

collaborators

12 papers

cs.IR2025

Multimodal Search in Chemical Documents and Reactions

Ayush Kumar Shah, Abhisek Dey, Leo Luo +9

We present a multimodal search tool that facilitates retrieval of chemical reactions, molecular structures, and associated text from scientific literature. Queries may combine mole…

cs.CV2024

Local and Global Graph Modeling with Edge-weighted Graph Attention Network for Handwritten Mathematical Expression Recognition

Yejing Xie, Richard Zanibbi, Harold Mouchère

In this paper, we present a novel approach to Handwritten Mathematical Expression Recognition (HMER) by leveraging graph-based modeling techniques. We introduce an End-to-end model…

cs.IR2024

ColBERT's [MASK]-based Query Augmentation: Effects of Quadrupling the Query Input Length

Ben Giacalone, Richard Zanibbi

A unique aspect of ColBERT is its use of [MASK] tokens in queries to score documents (query augmentation). Prior work shows [MASK] tokens weighting non-[MASK] query terms, emphasiz…

cs.IR2024

A Study of PHOC Spatial Region Configurations for Math Formula Retrieval

Matt Langsenkamp, Bryan Amador, Richard Zanibbi

A Pyramidal Histogram Of Characters (PHOC) represents the spatial location of symbols as binary vectors. The vectors are composed of levels that split a formula into equal-sized re…

cs.IR2024★ 2 cited

Mathematical Information Retrieval: Search and Question Answering

Richard Zanibbi, Behrooz Mansouri, Anurag Agarwal

Mathematical information is essential for technical work, but its creation, interpretation, and search are challenging. To help address these challenges, researchers have developed…

cs.CV2023★ 3 cited

ChemScraper: Leveraging PDF Graphics Instructions for Molecular Diagram Parsing

Ayush Kumar Shah, Bryan Manrique Amador, Abhisek Dey +4

Most molecular diagram parsers recover chemical structure from raster images (e.g., PNGs). However, many PDFs include commands giving explicit locations and shapes for characters,…

cs.IR2021

Effects of context, complexity, and clustering on evaluation for math formula retrieval

Behrooz Mansouri, Douglas W. Oard, Anurag Agarwal +1

There are now several test collections for the formula retrieval task, in which a system's goal is to identify useful mathematical formulae to show in response to a query posed as…

cs.CV2020★ 11 cited

ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images

Parag Mali, Puneeth Kukkadapu, Mahshad Mahdavi +1

We introduce the Scanning Single Shot Detector (ScanSSD) for locating math formulas offset from text and embedded in textlines. ScanSSD uses only visual features for detection: no…

cs.IR2019

Query Auto Completion for Math Formula Search

Shaurya Rohatgi, Wei Zhong, Richard Zanibbi +2

Query Auto Completion (QAC) is among the most appealing features of a web search engine. It helps users formulate queries quickly with less effort. Although there has been much eff…

cs.IR2015★ 6 cited

The Tangent Search Engine: Improved Similarity Metrics and Scalability for Math Formula Search

Richard Zanibbi, Kenny Davila, Andrew Kane +1

With the ever-increasing quantity and variety of data worldwide, the Web has become a rich repository of mathematical formulae. This necessitates the creation of robust and scalabl…

cs.IR2015★ 1 cited

Math Search for the Masses: Multimodal Search Interfaces and Appearance-Based Retrieval

Richard Zanibbi, Awelemdy Orakwue

We summarize math search engines and search interfaces produced by the Document and Pattern Recognition Lab in recent years, and in particular the min math search interface and the…

cs.CV2014★ 11 cited

Detecting Figures and Part Labels in Patents: Competition-Based Development of Image Processing Algorithms

Christoph Riedl, Richard Zanibbi, Marti A. Hearst +5

We report the findings of a month-long online competition in which participants developed algorithms for augmenting the digital version of patent documents published by the United…