Výsledky vyhledávání - "Shao, Jingyu"

Report

ErGAN: Generative Adversarial Networks for Entity Resolution

Autor: Shao, Jingyu, Wang, Qing, Wijesinghe, Asiri, Rahm, Erhard

Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets. A major challenge in learning-based entity resolution is how to reduce the label cost for training. Due to the quadratic nature of r

Externí odkaz: http://arxiv.org/abs/2012.10004

Zobrazit plný text záznamu

Report

Learning to Sample: an Active Learning Framework

Autor: Shao, Jingyu, Wang, Qing, Liu, Fangbing

Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the ``best'' active learning strategy. However, current learning-based active learning approaches still require sufficient training data so as to generaliz

Externí odkaz: http://arxiv.org/abs/1909.03585

Zobrazit plný text záznamu

Report

Skyblocking for Entity Resolution

Autor: Shao, Jingyu, Wang, Qing, Lin, Yu

In this paper, for the first time, we introduce the concept of skyblocking, which aims to efficiently identify the "most preferred" blocking scheme in terms of a given set of selection criteria for entity resolution blocking. To capture all possible

Externí odkaz: http://arxiv.org/abs/1805.12319

Zobrazit plný text záznamu

Report

Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions

Autor: Chakrabarti, Ayan, Shao, Jingyu, Shakhnarovich, Gregory

A single color image can contain many cues informative towards different aspects of local geometric structure. We approach the problem of monocular depth estimation by using a neural network to produce a mid-level representation that summarizes these

Externí odkaz: http://arxiv.org/abs/1605.07081

Zobrazit plný text záznamu