Zobrazeno 1 - 10
of 432
pro vyhledávání: '"Heutte, Laurent"'
Publikováno v:
Stat Comput 34, 9 (2024)
High dimension, low sample size (HDLSS) problems are numerous among real-world applications of machine learning. From medical images to text processing, traditional machine learning algorithms are usually unsuccessful in learning the best possible co
Externí odkaz:
http://arxiv.org/abs/2310.14710
Dynamic Time Wrapping (DTW) is a widely used algorithm for measuring similarities between two time series. It is especially valuable in a wide variety of applications, such as clustering, anomaly detection, classification, or video segmentation, wher
Externí odkaz:
http://arxiv.org/abs/2301.12873
Autor:
Dias, Caio da S., Britto Jr., Alceu de S., Barddal, Jean P., Heutte, Laurent, Koerich, Alessandro L.
This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. First, a region proposal algorithm detects object candidates in the document page images. Next, deep learning models
Externí odkaz:
http://arxiv.org/abs/2208.02397
Mining data streams is a challenge per se. It must be ready to deal with an enormous amount of data and with problems not present in batch machine learning, such as concept drift. Therefore, applying a batch-designed technique, such as dynamic select
Externí odkaz:
http://arxiv.org/abs/2008.08920
Many classification problems are naturally multi-view in the sense their data are described through multiple heterogeneous descriptions. For such tasks, dissimilarity strategies are effective ways to make the different descriptions comparable and to
Externí odkaz:
http://arxiv.org/abs/2007.08377
Multi-view learning is a learning task in which data is described by several concurrent representations. Its main challenge is most often to exploit the complementarities between these representations to help solve a classification/regression task. T
Externí odkaz:
http://arxiv.org/abs/2007.02572
Autor:
Wiggers, Kelly Lais, Junior, Alceu de Souza Britto, Koerich, Alessandro Lameiras, Heutte, Laurent, de Oliveira, Luiz Eduardo Soares
This paper describes two approaches for content-based image retrieval and pattern spotting in document images using deep learning. The first approach uses a pre-trained CNN model to cope with the lack of training data, which is fine-tuned to achieve
Externí odkaz:
http://arxiv.org/abs/1907.09404
Autor:
Wiggers, Kelly L., Britto Jr., Alceu S., Heutte, Laurent, Koerich, Alessandro L., Oliveira, Luiz S.
This paper presents a novel approach for image retrieval and pattern spotting in document image collections. The manual feature engineering is avoided by learning a similarity-based representation using a Siamese Neural Network trained on a previousl
Externí odkaz:
http://arxiv.org/abs/1906.09513
Pattern spotting consists of searching in a collection of historical document images for occurrences of a graphical object using an image query. Contrary to object detection, no prior information nor predefined class is given about the query so train
Externí odkaz:
http://arxiv.org/abs/1906.08580
Publikováno v:
In Pattern Recognition Letters July 2023 171:162-169
