Neurocomputing

With the explosive growth of videos captured everyday, how to efficiently extract useful information from videos has become a more and more important problem. As one of the most effective methods, video summarization aiming to extract ...

With the goal of developing an accurate and fast image reconstruction algorithm for ultrasound computed tomography, we combine elements of model- and data-driven approaches and propose a learned method which addresses the disadvantages ...

The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in ...

• We propose a new framework for the knee articular cartilage segmentation.
• Novel ...

Segmentation of knee articular cartilage tissue (ACT) from 3D magnetic resonance images (MRIs) is a fundamental task in assessing knee osteoarthritis (KOA). However, automated ACT segmentation of knee cartilage is complicated by (1) ...

In this paper, an approach for distributing the deep neural network (DNN) training onto IoT edge devices is proposed. The approach results in protecting data privacy on the edge devices and decreasing the load on cloud servers. In ...

• We have proposed a new gradient descent TLS adaptive filtering algorithm for sparse system identification under EIV model.

The total least squares (TLS) method has been successfully applied to system identification in the errors-in-variables (EIV) model, which can efficiently describe systems where input–output pairs are contaminated by noise. In this ...

• We propose a fast, compact and parameter-efficient party-ignorant framework based on emotional recurrent unit.

Sentiment analysis in conversations has gained increasing attention in recent years for the growing amount of applications it can serve, e.g., sentiment analysis, recommender systems, and human-robot interaction. The main difference ...

• Trait agnostic generic approach for constructing deep cancelable biometric templates.

In a post-COVID-19 world, extensive study of deep learning-based biometric authentication techniques prompts the need to secure them. Further, the biometric data is assumed to be largely immutable; thus, if it is compromised, it is ...

• Proposing a novel framework for referring expression comprehension and segmentation.

Referring expression comprehension and segmentation aim to locate and segment a referred instance in an image according to a natural language expression. However, existing methods tend to ignore the interaction between visual and ...

In this paper, we consider various schemes of sequence resampling in reservoir computing models for nonlinear time series prediction. These schemes can enrich the features used for training the readout part with batch learning and lead ...

Multimodal Sentiment Analysis (MSA) is a challenging research area that investigates sentiment expressed from multiple heterogeneous sources of information. To integrate multimodal information including text, visual and audio ...

Deep cross-modal hashing which integrates deep learning and hashing into cross-modal retrieval, achieves better performance than traditional cross-modal retrieval methods. Nevertheless, most previous deep cross-modal hashing methods ...

Generative learning in pixel domain has achieved great success in exploiting their correlations in processing images towards desired objectives, yet learning in frequency domain could provide added benefits in exploiting pixel ...

A novel model called Instinct Plasticity Echo State Network with New Weights Selection Method, which is Optimized by Genetic Algorithm, is proposed (IP-NESN-GA). There are three proposed methods that are employed in the conventional ...

In multi-label learning, feature selection is a topical issue for addressing high-dimension data. However, most of existing methods adopt imperfect labels to perform feature selection. Although some graph-based multi-label feature ...

The nonstationary time series prediction is challenging since it demands knowledge of both data transformation and prediction methods. This paper presents TSPred, a framework for nonstationary time series prediction. It differs from ...

It is challenging to recover the large-scale internet traffic data purely from the link-load measurements. With the rapid growth of the problem scale, it will be extremely difficult to sustain the recovery accuracy and the ...

The recent advances usually mine market information from the chaotic data to conduct a stock movement prediction task. However, the current stock price movement prediction approaches mainly compute attention weighted sum of the global ...

Person Re-identification (Re-ID) has attracted more and more attention thanks to its great practical value in the field of video surveillance. Most works have focused on solving the problem of supervised Re-ID on a single domain and ...

Recently, removing rain streaks from a single image has attracted a lot of attention because rain streaks can severely degrade the perceptual quality of the image and cause many practical vision systems to fail. Single image deraining ...

k-means clustering is widely used in many fields such as data mining, machine learning, and information retrieval. In many cases, users need to cooperate to perform k-means clustering tasks. How to perform clustering without revealing ...

Noise and physical constraints of redundant manipulators are the two major challenges in the repetitive motion planning (RMP) problems. Therefore, this paper proposed a power-exponent-type modified recurrent neural network (PET-MRNN) ...

Display Omitted

Relation extraction is a critical natural language processing task. Existing dependency-based models captured long-range syntactic relations, but they usually cannot fully exploit information from sentences. They often used hand-...

An event-triggered tracking control problem is investigated for a class of unknown nonlinear systems in this paper. First, to approximate the unknown function, the radial basis function neural network is used. Then, we propose an event-...

Deep Reinforcement Learning (DRL) has proven its capability to learn optimal policies in decision-making problems by directly interacting with environments. Meanwhile, supervised learning methods also show great capability of learning ...

Automated pancreatic cancer segmentation is crucial for successful clinical aid diagnosis and surgical planning. However, the tiny size and inconspicuous boundaries of pancreatic cancer lesions lead to poor segmentation performance ...

• We represent images and questions as graphs, and propose to answer visual questions with pattern matching.

Traditional techniques for visual question answering (VQA) are mostly end-to-end neural network based, which often perform poorly (e.g., low accuracy) due to lack of understanding and reasoning. To overcome the weaknesses, we propose a ...

This paper is concerned with the disturbance estimation and velocity recovery of autonomous surface ve hicles subject to unknown input gains, in addition to lumped uncertainties composed of unknown internal dynamics and external ...

The mechanism of human vision can easily detect and segment objects based on boundary information. Even though the deep learning instance segmentation model based on boundary information can mimic this human vision mechanism, its ...