Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance. We propose a novel deep neural networks (DNN) based model, Canonical Correlated AutoEncoder (C2AE), for solving this task. Aiming at better relating feature and label domain data for improved classification, ...

Within natural language processing, multi-label classification is an important but challenging task. It more complex than single-label since the document representations need to cover fine-grained label information, while labels predicted by model are often related. Recently, large pre-trained models have achieved great performance on tasks, typically using embedding of [CLS] vector as semantic...

A novel framework for music tagging is proposed. First, each music recording is represented by bio-inspired auditory temporal modulations. Then, a multilinear subspace learning algorithm based on sparse label coding is developed to effectively harness the multi-label information for dimensionality reduction. The proposed algorithm is referred to as Sparse Multi-label Linear Embedding Nonnegativ...

We introduce in this work an efficient approach for audio scene classification using deep recurrent neural networks. An audio scene is firstly transformed into a sequence of high-level label tree embedding feature vectors. The vector sequence is then divided into multiple subsequences on which a deep GRUbased recurrent neural network is trained for sequence-to-label classification. The global p...

Abstract. In multi-label learning, each sample is associated with several labels. Existing works indicate that exploring correlations between labels improve the prediction performance. However, embedding the label correlations into the training process significantly increases the problem size. Moreover, the mapping of the label structure in the feature space is not clear. In this paper, we prop...

the efficient detection of charged biomolecules by biosensor with appropriate semiconducting nanomaterials and with optimum device geometry has caught tremendous research interest in the present decade. here, the performance of various label-free electronic biosensors to detect bio-molecules is investigated by simulation technique. silicon nanowire sensor, nanosphere sensor and double gate fiel...

We present a high-capacity informed embedding scheme based on a trellis structure for a nested linear block code. This scheme can embed adaptive robust watermarked messages for various applications. Instead of using randomly generated reference vectors as arc labels, this scheme uses the codewords of a nested block code to label the arcs in the trellis structure so that each codeword can carry ...

Network embedding is a classical task which aims to map the nodes of a network to lowdimensional vectors. Most of the previous network embedding methods are trained in an unsupervised scheme. Then the learned node embeddings can be used as inputs of many machine learning tasks such as node classification, attribute inference. However, the discriminant power of the node embeddings maybe improved...

Deep learning can be an effective and efficient means to automatically detect and classify targets in synthetic aperture radar (SAR) images, but it is critical for trained neural networks to be robust to variations that exist between training and test environments. The layers in a neural network can be understood to be successive transformations of an input image into embedded feature represent...

In many applications, the data may be high dimensional, represented by multiple features, and associated with more than one labels. Embedding learning is an effective strategy for dimensionality reduction and for nearest neighbor search in massive datasets. We propose a novel method to seek compact embedding that allows efficient retrieval with incompletely-labeled multi-view data. Based on mul...