中文
相关论文

相关论文: Autonomous Cleaning of Corrupted Scanned Documents…

200 篇论文

Automatic font generation without human experts is a practical and significant problem, especially for some languages that consist of a large number of characters. Existing methods for font generation are often in supervised learning. They…

计算机视觉与模式识别 · 计算机科学 2023-01-02 Xinyuan Chen , Yangchen Xie , Li Sun , Yue Lu

Although diffusion models exhibit impressive generative capabilities, existing methods for stylized image generation based on these models often require textual inversion or fine-tuning with style images, which is time-consuming and limits…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Xin Ma , Yaohui Wang , Xinyuan Chen , Tien-Tsin Wong , Cunjian Chen

This paper presents a model-based, unsupervised algorithm for recovering word boundaries in a natural-language text from which they have been deleted. The algorithm is derived from a probability model of the source that generated the text.…

计算与语言 · 计算机科学 2007-05-23 Michael R. Brent

Most existing feature learning methods optimize inflexible handcrafted features and the affinity matrix is constructed by shallow linear embedding methods. Different from these conventional methods, we pretrain a generative neural network…

计算机视觉与模式识别 · 计算机科学 2019-10-02 Changlu Chen , Chaoxi Niu , Xia Zhan , Kun Zhan

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for…

计算与语言 · 计算机科学 2021-09-16 Giangiacomo Mercatali , André Freitas

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to…

计算与语言 · 计算机科学 2016-10-27 Qian Chen , Xiaodan Zhu , Zhenhua Ling , Si Wei , Hui Jiang

We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when…

图像与视频处理 · 电气工程与系统科学 2018-11-29 Shu Kong , Charless Fowlkes

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling…

机器人学 · 计算机科学 2018-11-20 Eric Jang , Coline Devin , Vincent Vanhoucke , Sergey Levine

As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes human-authored text. Since online data is the primary resource…

计算与语言 · 计算机科学 2025-09-23 George Drayson , Emine Yilmaz , Vasileios Lampos

Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of…

计算与语言 · 计算机科学 2020-05-11 Daphne Ippolito , Daniel Duckworth , Chris Callison-Burch , Douglas Eck

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…

机器学习 · 统计学 2017-03-07 Matt J. Kusner , Brooks Paige , José Miguel Hernández-Lobato

This paper studies the problem of detecting anomalous graphs using a machine learning model trained on only normal graphs, which has many applications in molecule, biology, and social network data analysis. We present a self-discriminative…

机器学习 · 计算机科学 2023-10-11 Jinyu Cai , Yunhe Zhang , Jicong Fan

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

机器学习 · 计算机科学 2018-09-14 Zhiting Hu , Zichao Yang , Xiaodan Liang , Ruslan Salakhutdinov , Eric P. Xing

Pool of knowledge available to the mankind depends on the source of learning resources, which can vary from ancient printed documents to present electronic material. The rapid conversion of material available in traditional libraries to…

计算机视觉与模式识别 · 计算机科学 2014-12-25 Akmal Jahan Mac , Roshan G Ragel

When images are statistically described by a generative model we can use this information to develop optimum techniques for various image restoration problems as inpainting, super-resolution, image coloring, generative model inversion, etc.…

图像与视频处理 · 电气工程与系统科学 2020-06-17 Kalliopi Basioti , George V. Moustakides

Online reviews are an important source of feedback for understanding customers. In this study, we follow novel approaches that target this absence of actionable insights by classifying reviews as defect reports and requests for improvement.…

计算与语言 · 计算机科学 2020-04-21 Gino V. H. Mangnoesing , Maria Mihaela Trusca , Flavius Frasincar

This paper explores an empirical approach to learn more discriminantive sentence representations in an unsupervised fashion. Leveraging semantic graph smoothing, we enhance sentence embeddings obtained from pretrained models to improve…

计算与语言 · 计算机科学 2024-02-21 Chakib Fettal , Lazhar Labiod , Mohamed Nadif

We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (\emph{chargrid}) representation of a document…

计算机视觉与模式识别 · 计算机科学 2020-02-28 Christian Reisswig , Anoop R Katti , Marco Spinaci , Johannes Höhne

Searching for all occurrences of a pattern in a text is a fundamental problem in computer science with applications in many other fields, like natural language processing, information retrieval and computational biology. Sampled string…

数据结构与算法 · 计算机科学 2019-08-19 Simone Faro , Arianna Pavone , Francesco Pio Marino

There has been a lot of recent interest in mining patterns from graphs. Often, the exact structure of the patterns of interest is not known. This happens, for example, when molecular structures are mined to discover fragments useful as…

数据结构与算法 · 计算机科学 2007-05-23 Pavel Dmitriev , Carl Lagoze