1 citations · 1 across the 3 of their papers we have counts for
4 papers · 1 filter
Improving MLLM Historical Record Extraction with Test-Time Image
Taylor Archibald, Tony Martinez
We present a novel ensemble framework that stabilizes LLM based text extraction from noisy historical documents. We transcribe multiple augmented variants of each image with Gemini…
Leveraging Semantic Segmentation Masks with Embeddings for Fine-Grained Form Classification
Taylor Archibald, Tony Martinez
Efficient categorization of historical documents is crucial for fields such as genealogy, legal research, and historical scholarship, where manual classification is impractical for…
DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documents
Taylor Archibald, Tony Martinez
Document semantic segmentation is a promising avenue that can facilitate document analysis tasks, including optical character recognition (OCR), form classification, and document e…
TRACE: A Differentiable Approach to Line-level Stroke Recovery for Offline Handwritten Text
Taylor Archibald, Mason Poggemann, Aaron Chan +1
Stroke order and velocity are helpful features in the fields of signature verification, handwriting recognition, and handwriting synthesis. Recovering these features from offline h…