Neurocomputing

We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation. Our study shows that excellent results can be achieved with a ...

Existing online recruitment platforms depend on automatic ways of conducting the person-job fit, whose goal is matching appropriate job seekers with job positions. Intuitively, the previous successful recruitment records contain ...

The multi-hop reading comprehension (RC) is challenging for machine reading comprehension. It is crucial for multi-hop RC to comprehend complex questions and contents between multiple paragraphs. In this paper, we propose a strategy of ...

Mixtures of von Mises-Fisher distributions can be used to cluster data on the unit hypersphere. This is particularly adapted for high-dimensional directional data such as texts. We propose in this article to estimate a von Mises ...

Recently, deep learning technology has achieved remarkable progress in compressed video quality enhancement. However, the existing methods fail to consider the fact that the regions with different compression losses contain varied ...

• A novel supervised method is proposed for defocus blur detection.
• Residual ...

Defocus blur detection (DBD) aims to extract the in-focus part from a single image. Instead of adopting traditional hand-crafted features, recent deep neural networks based methods achieve DBD in an end-to-end architecture, obtaining ...

Deformable medical image registration plays a vital role in clinical diagnosis, monitoring treatment, and postoperative recovery. Nevertheless, the existing registration algorithms rely on a single network or training strategy to ...

Learning-based depth estimation from light fields has made significant advances in recent years, however, most of these work abandon the traditional non-learning based formulations and start over with an end-to-end deep network ...

• Pioneering research on traffic command recognition distinguishing directions and gestures.

Understanding traffic officer commands is a fundamental perception task for intelligent vehicles in driver assistance and autonomous driving. Previous studies have emphasized explicit traffic command gesture recognition but have not ...

Nowadays, the general artificial intelligence field aims to emulate some human behavior features in computational models for different objectives. This article proposes a model grounded in neurosciences focusing on individual behavior ...

Temperature is one of the most important meteorological elements, which affects the daily lives of people all over the world. Owing to the rapid development of meteorological facilities, the number of meteorological observation ...

Time series play an important role in many fields, such as industrial control, automated monitoring, and weather forecasting. Because there is often more than one variable in reality problems and they are related to each other, the ...

• Propose a novel enhanced distance-aware self-attention network for sentence modeling.

Sentence semantic matching is a core research area in natural language processing, which is widely used in various natural language tasks. In recent years, attention mechanism has shown good performance in deep neural networks for ...

The graph-based multi-view clustering has received extensive attention in recent years due to its competitiveness in characterizing the relationship between data and its well defined mathematic. However, the existing graph-based ...

• We propose a general framework that is suitable for the de-identification of people in face images.

Because of the explosive growth of face photos as well as their widespread dissemination and easy accessibility in social media, the security and privacy of personal identity information become an unprecedented challenge. Meanwhile, ...

Label distribution learning (LDL) is a new machine learning paradigm to solve label ambiguity and has drawn increasing attention in recent years. The importance of all labels needs to be considered under the LDL settings. A series of ...

• The spiking neural P systems with cooperative synapses (SNPCS systems) is proposed.

Spiking neural P systems (SN P systems) are a class of neuron-inspired computation models, where each synapse independently passes a spike produced by the pre-synaptic neuron to the post-synaptic neuron. Motivated by the mechanism of ...

Optical motion capture systems have been used intensively to obtain human body poses. However, there still exist several problems. First is the dislocation problem caused by joints being too close together. The second is the joint lost ...

Due to its impressive representation power, the graph convolutional network (GCN) has attracted increasing attention in the hyperspectral image (HSI) classification. However, the most of available GCN-based methods for HSI ...

There are challenges exist in the segmentation of smoke contours on images currently, the requirements for limited processing resources and low-latency operations based on monitoring platform, and the balance between high accuracy and ...

Instance search aims at retrieving a particular object instance from a set of scene images. Although studied in previous competitions like TRECVID, there have been limited literature or datasets on this topic. In this paper, to ...

In modern convolutional neural networks (CNNs), the pooling layer is seen as one of the primary layers for building the CNN model, which effectively downscales the spatial size of feature maps to reduce memory consumption. Several ...

Recently, researches on universal adversarial perturbations have deepened the public’s attention to the security of deep neural networks (DNNs). Most researchers use iterative methods or generative adversarial networks (GANs) to find ...

Semantic Inpainting on Segmentation Map (SISM) aims to manipulate segmentation maps by semantics. Recent works show SISM provides semantic-aware auxiliary information for better style or structure manipulations. Providing structural ...

Colorization is an effective technology to improve the imaging quality of thermal infrared sensors, which is of great importance to environmental perception systems. Recently, colorization for thermal infrared images has realized ...

In machine learning and pattern recognition tasks, classification performance is often degraded due to the existence of irrelevant and redundant features, especially for high-dimensional data. As a data preprocessing tool, feature ...

Deep learning oriented named entity recognition (DNER) has gradually become the paradigm of knowledge discovery, which greatly promotes domain intelligence. However, the activation function of DNER fails to treat gradient vanishing, no ...

• Attention regions cropping and erasing data augmentation approaches are proposed for fine-grained visual classification.

Fine-grained visual classification is challenging due to similarities within classes and discriminative features located in subtle regions. Conventional methods focus on extracting features from the most discriminative parts, which may ...