Výsledky vyhledávání - "Popat, Ashok C."

Report

Post-OCR Paragraph Recognition by Graph Convolutional Networks

Autor: Wang, Renshen, Fujii, Yasuhisa, Popat, Ashok C.

We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes. Two steps, namely line splitting and line clustering, are performed to extract paragraphs from the lines i

Externí odkaz: http://arxiv.org/abs/2101.12741

Zobrazit plný text záznamu

Report

Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision

Autor: Jansen, Aren, Ellis, Daniel P. W., Hershey, Shawn, Moore, R. Channing, Plakal, Manoj, Popat, Ashok C., Saurous, Rif A.

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal uns

Externí odkaz: http://arxiv.org/abs/1911.05894

Zobrazit plný text záznamu

Report

A Scalable Handwritten Text Recognition System

Autor: Ingle, R. Reeve, Fujii, Yasuhisa, Deselaers, Thomas, Baccash, Jonathan, Popat, Ashok C.

Many studies on (Offline) Handwritten Text Recognition (HTR) systems have focused on building state-of-the-art models for line recognition on small corpora. However, adding HTR capability to a large scale multilingual OCR system poses new challenges.

Externí odkaz: http://arxiv.org/abs/1904.09150

Zobrazit plný text záznamu

Report

Sequence-to-Label Script Identification for Multilingual OCR

Autor: Fujii, Yasuhisa, Driesen, Karel, Baccash, Jonathan, Hurst, Ash, Popat, Ashok C.

We describe a novel line-level script identification method. Previous work repurposed an OCR model generating per-character script codes, counted to obtain line-level script identification. This has two shortcomings. First, as a sequence-to-sequence

Externí odkaz: http://arxiv.org/abs/1708.04671

Zobrazit plný text záznamu