Search Results for author: Yen-Yun Yu

Found 6 papers, 0 papers with code

BART for Post-Correction of OCR Newspaper Text

no code implementations WNUT (ACL) 2021 Elizabeth Soper, Stanley Fujimoto, Yen-Yun Yu

Optical character recognition (OCR) from newspaper page images is susceptible to noise due to degradation of old documents and variation in typesetting.

Language Modelling Optical Character Recognition +2

PercentMatch: Percentile-based Dynamic Thresholding for Multi-Label Semi-Supervised Classification

no code implementations30 Aug 2022 Junxiang Huang, Alexander Huang, Beatriz C. Guerra, Yen-Yun Yu

While much of recent study in semi-supervised learning (SSL) has achieved strong performance on single-label classification problems, an equally important yet underexplored problem is how to leverage the advantage of unlabeled data in multi-label classification tasks.

Classification Multi-Label Classification

Ventral-Dorsal Neural Networks: Object Detection via Selective Attention

no code implementations15 May 2020 Mohammad K. Ebrahimpour, Jiayun Li, Yen-Yun Yu, Jackson L. Reese, Azadeh Moghtaderi, Ming-Hsuan Yang, David C. Noelle

The coarse functional distinction between these streams is between object recognition -- the "what" of the signal -- and extracting location related information -- the "where" of the signal.

Image Classification object-detection +2

Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks

no code implementations11 Oct 2019 Mostafa Karimi, Gopalkrishna Veni, Yen-Yun Yu

We tackle this problem by developing a handwritten-to-machine-print conditional Generative Adversarial network (HW2MP-GAN) model that formulates handwritten recognition as a text-Image-to-text-Image translation problem where a given image, typically in an illegible form, is converted into another image, close to its machine-print form.

Image-to-Image Translation Translation

Image captioning with weakly-supervised attention penalty

no code implementations6 Mar 2019 Jiayun Li, Mohammad K. Ebrahimpour, Azadeh Moghtaderi, Yen-Yun Yu

Ideally, attention maps predicted by captioning models should be consistent with intrinsic attentions from visual models for any given visual concept.

Image Captioning

Clustering With Pairwise Relationships: A Generative Approach

no code implementations6 May 2018 Yen-Yun Yu, Shireen Y. Elhabian, Ross T. Whitaker

Semi-supervised learning (SSL) has become important in current data analysis applications, where the amount of unlabeled data is growing exponentially and user input remains limited by logistics and expense.

Cannot find the paper you are looking for? You can Submit a new open access paper.