introduction:in this study, ecg signals have been embedded into medical images to create a novel blind watermarking method. the embedding is done when the original image is compressed using the ezw algorithm. the extraction process is performed at the decompression time of the watermarked image. materials and methods: the multi-resolution watermarking with a secret key algorithm developed in th...

Recently, many deep learning-based methods have been developed for solving remote sensing (RS) scene classification or retrieval tasks. Most of the adopted loss functions training these models require accurate annotations. However, presence noise in such annotations (also known as label noise) cannot be avoided large-scale RS benchmark archives, resulting from geo-location/registration errors, ...

Network embedding, aiming to project a network into low-dimensional space, is increasingly becoming focus of research. Semi-supervised embedding takes advantage labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no nodes at all. To alleviate this, we propose...

Transfer learning has attracted a lot of attention in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of different domains such that the divergence between domains can be reduced with the new representation. Recently, deep learning has been proposed to learn more robust or higherlevel features for transfer learning. However, to...

We present V2V, a method for embedding each vertex in a graph as a vector in a fixed dimensional space. Inspired by methods for word embedding such as word2vec, a vertex embedding is computed through enumerating random walks in the graph, and using the resulting vertex sequences to provide the context for each vertex. This embedding allows one to use well-developed techniques from machine learn...

Concept-based representation — combined with some classifier (e.g., support vector machine) or regression analysis (e.g., linear regression) — induces a popular approach among image processing community, used to infer image labels. We propose a supervised learning procedure to obtain an embedding to a latent concept space with the pre-defined inner product. This learning procedure uses rank min...

The paper presents a text classification approach for classifying tweets into two classes: availability/ need, based on the content of the tweets. The approach uses a language model for classification based on word-embedding of fixed length to get the semantic relationship among words. The approach uses logistic regression for actual classification. The logistic regression measures the relation...

Matrix completion as a common problem in many application domains has received increasing attention in the machine learning community. Previous matrix completion methods have mostly focused on exploiting the matrix low-rank property to recover missing entries. Recently, it has been noticed that side information that describes the matrix items can help to improve the matrix completion performanc...