Interest Point Recommendation based on Multi Feature Representation and Attention Mechanism

The sentiment analysis of microblog text has always been a challenging research field due to the limited and complex contextual information. However, most of the existing sentiment analysis methods for microblogs focus on classifying the polarity of emotional keywords while ignoring the transition or progressive impact of words in different positions in the Chinese syntactic structure on global sentiment, as well as the utilization of emojis. To this end, we propose the emotion-semantic-enhanced bidirectional long short-term memory (BiLSTM) network with the multi-head attention mechanism model (EBILSTM-MH) for sentiment analysis. This model uses BiLSTM to learn feature representation of input texts, given the word embedding. Subsequently, the attention mechanism is used to assign the attentive weights of each words to the sentiment analysis based on the impact of emojis. The attentive weights can be combined with the output of the hidden layer to obtain the feature representation of posts. Finally, the sentiment polarity of microblog can be obtained through the dense connection layer. The experimental results show the feasibility of our proposed model on microblog sentiment analysis when compared with other baseline models.

Download Full-text

AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism

2019 IEEE/CVF International Conference on Computer Vision (ICCV) ◽

10.1109/iccv.2019.00658 ◽

2019 ◽

Author(s):

Jingjia Huang ◽

Zhangheng Li ◽

Nannan Li ◽

Shan Liu ◽

Ge Li

Keyword(s):

Attention Mechanism ◽

Feature Representation ◽

Convolutional Networks

Download Full-text

Hybrid Attention Network for Language-Based Person Search

Sensors ◽

10.3390/s20185279 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5279

Author(s):

Yang Li ◽

Huahu Xu ◽

Junsheng Xiao

Keyword(s):

Image Features ◽

Attention Mechanism ◽

Feature Representation ◽

Semantic Features ◽

Retrieval Task ◽

Attention Network ◽

Fine Grained ◽

Person Search ◽

High Level ◽

Language Description

Language-based person search retrieves images of a target person using natural language description and is a challenging fine-grained cross-modal retrieval task. A novel hybrid attention network is proposed for the task. The network includes the following three aspects: First, a cubic attention mechanism for person image, which combines cross-layer spatial attention and channel attention. It can fully excavate both important midlevel details and key high-level semantics to obtain better discriminative fine-grained feature representation of a person image. Second, a text attention network for language description, which is based on bidirectional LSTM (BiLSTM) and self-attention mechanism. It can better learn the bidirectional semantic dependency and capture the key words of sentences, so as to extract the context information and key semantic features of the language description more effectively and accurately. Third, a cross-modal attention mechanism and a joint loss function for cross-modal learning, which can pay more attention to the relevant parts between text and image features. It can better exploit both the cross-modal and intra-modal correlation and can better solve the problem of cross-modal heterogeneity. Extensive experiments have been conducted on the CUHK-PEDES dataset. Our approach obtains higher performance than state-of-the-art approaches, demonstrating the advantage of the approach we propose.

Download Full-text

Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.3301946 ◽

2019 ◽

Vol 33 ◽

pp. 946-953 ◽

Cited By ~ 11

Author(s):

Binbin Hu ◽

Zhiqiang Zhang ◽

Chuan Shi ◽

Jun Zhou ◽

Xiaolong Li ◽

...

Keyword(s):

Financial Services ◽

Attention Mechanism ◽

Feature Representation ◽

Information Network ◽

Heterogeneous Information Network ◽

Heterogeneous Information ◽

Structure Information ◽

Detection Model ◽

Meta Path ◽

Interaction Relations

As one of the major frauds in financial services, cash-out fraud is that users pursue cash gains with illegal or insincere means. Conventional solutions for the cash-out user detection are to perform subtle feature engineering for each user and then apply a classifier, such as GDBT and Neural Network. However, users in financial services have rich interaction relations, which are seldom fully exploited by conventional solutions. In this paper, with the real datasets in Ant Credit Pay of Ant Financial Services Group, we first study the cashout user detection problem and propose a novel hierarchical attention mechanism based cash-out user detection model, called HACUD. Specifically, we model different types of objects and their rich attributes and interaction relations in the scenario of credit payment service with an Attributed Heterogeneous Information Network (AHIN). The HACUD model enhances feature representation of objects through meta-path based neighbors exploiting different aspects of structure information in AHIN. Furthermore, a hierarchical attention mechanism is elaborately designed to model user’s preferences towards attributes and meta-paths. Experimental results on two real datasets show that the HACUD outperforms the state-of-the-art methods.

Download Full-text

Human Action Recognition Based on Normalized Interest Points and Super-Interest Points

International Journal of Humanoid Robotics ◽

10.1142/s0219843614500054 ◽

2014 ◽

Vol 11 (01) ◽

pp. 1450005

Author(s):

Yangyang Wang ◽

Yibo Li ◽

Xiaofei Ji

Keyword(s):

Action Recognition ◽

Clustering Algorithm ◽

Three Dimensional ◽

Temporal Correlation ◽

Human Action Recognition ◽

Human Action ◽

Feature Representation ◽

Interest Point ◽

Interest Points ◽

Active Research

Visual-based human action recognition is currently one of the most active research topics in computer vision. The feature representation directly has a crucial impact on the performance of the recognition. Feature representation based on bag-of-words is popular in current research, but the spatial and temporal relationship among these features is usually discarded. In order to solve this issue, a novel feature representation based on normalized interest points is proposed and utilized to recognize the human actions. The novel representation is called super-interest point. The novelty of the proposed feature is that the spatial-temporal correlation between the interest points and human body can be directly added to the representation without considering scale and location variance of the points by introducing normalized points clustering. The novelty concerns three tasks. First, to solve the diversity of human location and scale, interest points are normalized based on the normalization of the human region. Second, to obtain the spatial-temporal correlation among the interest points, the normalized points with similar spatial and temporal distance are constructed to a super-interest point by using three-dimensional clustering algorithm. Finally, by describing the appearance characteristic of the super-interest points and location relationship among the super-interest points, a new feature representation is gained. The proposed representation formation sets up the relationship among local features and human figure. Experiments on Weizmann, KTH, and UCF sports dataset demonstrate that the proposed feature is effective for human action recognition.

Download Full-text

An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/277 ◽

2019 ◽

Cited By ~ 1

Author(s):

Elaheh Barati ◽

Xuewen Chen

Keyword(s):

Reinforcement Learning ◽

State Of The Art ◽

Attention Mechanism ◽

Feature Representation ◽

Decision Making Process ◽

Multiple Views ◽

Single Feature ◽

3D Environments ◽

Noisy Conditions ◽

Level Of Importance

In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a deep reinforcement learning method and an attention mechanism in a multi-view environment. Each view can provide various representative information about the environment. Through our attention mechanism, our method generates a single feature representation of environment given its multiple views. It learns a policy to dynamically attend to each view based on its importance in the decision-making process. Through experiments, we show that our method outperforms its state-of-the-art baselines on TORCS racing car simulator and three other complex 3D environments with obstacles. We also provide experimental results to evaluate the performance of our method on noisy conditions and partial observation settings.

Download Full-text

Biomedical document triage using a hierarchical attention-based capsule network

BMC Bioinformatics ◽

10.1186/s12859-020-03673-5 ◽

2020 ◽

Vol 21 (S13) ◽

Author(s):

Jian Wang ◽

Mengying Li ◽

Qishuai Diao ◽

Hongfei Lin ◽

Zhihao Yang ◽

...

Keyword(s):

Neural Networks ◽

Information Extraction ◽

Precision Medicine ◽

State Of The Art ◽

Attention Mechanism ◽

Feature Representation ◽

Experimental Results ◽

Biomedical Domain ◽

Proposed Model ◽

Document Triage

Abstract Background Biomedical document triage is the foundation of biomedical information extraction, which is important to precision medicine. Recently, some neural networks-based methods have been proposed to classify biomedical documents automatically. In the biomedical domain, documents are often very long and often contain very complicated sentences. However, the current methods still find it difficult to capture important features across sentences. Results In this paper, we propose a hierarchical attention-based capsule model for biomedical document triage. The proposed model effectively employs hierarchical attention mechanism and capsule networks to capture valuable features across sentences and construct a final latent feature representation for a document. We evaluated our model on three public corpora. Conclusions Experimental results showed that both hierarchical attention mechanism and capsule networks are helpful in biomedical document triage task. Our method proved itself highly competitive or superior compared with other state-of-the-art methods.

Download Full-text

Unsupervised Trademark Retrieval Method Based on Attention Mechanism

Sensors ◽

10.3390/s21051894 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1894

Author(s):

Jiangzhong Cao ◽

Yunfei Huang ◽

Qingyun Dai ◽

Wing-Kuen Ling

Keyword(s):

Supervised Learning ◽

Attention Mechanism ◽

Feature Representation ◽

Experimental Results ◽

Learning Methods ◽

Retrieval Method ◽

Average Rank ◽

Good Feature ◽

Key Features ◽

Better Than

Aiming at the high cost of data labeling and ignoring the internal relevance of features in existing trademark retrieval methods, this paper proposes an unsupervised trademark retrieval method based on attention mechanism. In the proposed method, the instance discrimination framework is adopted and a lightweight attention mechanism is introduced to allocate a more reasonable learning weight to key features. With an unsupervised way, this proposed method can obtain good feature representation of trademarks and improve the performance of trademark retrieval. Extensive comparative experiments on the METU trademark dataset are conducted. The experimental results show that the proposed method is significantly better than traditional trademark retrieval methods and most existing supervised learning methods. The proposed method obtained a smaller value of NAR (Normalized Average Rank) at 0.051, which verifies the effectiveness of the proposed method in trademark retrieval.

Download Full-text

Efficient Attention Mechanism for Dynamic Convolution in Lightweight Neural Network

Applied Sciences ◽

10.3390/app11073111 ◽

2021 ◽

Vol 11 (7) ◽

pp. 3111

Author(s):

Enjie Ding ◽

Yuhao Cheng ◽

Chengcheng Xiao ◽

Zhongyu Liu ◽

Wanli Yu

Keyword(s):

Neural Networks ◽

Spatial Information ◽

Attention Mechanism ◽

Feature Representation ◽

Feature Maps ◽

Convolutional Network ◽

Dynamic Neural Networks ◽

Reduction Methods ◽

Channel Reduction ◽

Channel Information

Light-weight convolutional neural networks (CNNs) suffer limited feature representation capabilities due to low computational budgets, resulting in degradation in performance. To make CNNs more efficient, dynamic neural networks (DyNet) have been proposed to increase the complexity of the model by using the Squeeze-and-Excitation (SE) module to adaptively obtain the importance of each convolution kernel through the attention mechanism. However, the attention mechanism in the SE network (SENet) selects all channel information for calculations, which brings essential challenges: (a) interference caused by the internal redundant information; and (b) increasing number of network calculations. To address the above problems, this work proposes a dynamic convolutional network (termed as EAM-DyNet) to reduce the number of channels in feature maps by extracting only the useful spatial information. EAM-DyNet first uses the random channel reduction and channel grouping reduction methods to remove the redundancy in the information. As the downsampling of information can lead to the loss of useful information, it then applies an adaptive average pooling method to maintain the information integrity. Extensive experimental results on the baseline demonstrate that EAM-DyNet outperformed the existing approaches, thus it can achieve higher accuracy of the network test and less network parameters.

Download Full-text

Student-Performulator: Student Academic Performance Using Hybrid Deep Neural Network

Sustainability ◽

10.3390/su13179775 ◽

2021 ◽

Vol 13 (17) ◽

pp. 9775

Author(s):

Bashir Khan Yousafzai ◽

Sher Afzal ◽

Taj Rahman ◽

Inayat Khan ◽

Inam Ullah ◽

...

Keyword(s):

Neural Network ◽

Data Mining ◽

Student Performance ◽

Performance Prediction ◽

Deep Neural Network ◽

Short Term Memory ◽

Educational Data Mining ◽

Attention Mechanism ◽

Feature Representation ◽

Superior Performance

Educational data generated through various platforms such as e-learning, e-admission systems, and automated result management systems can be effectively processed through educational data mining techniques in order to gather highly useful insights into students’ performance. The prediction of student performance from historical academic data is a highly desirable application of educational data mining. In this regard, there is an urgent need to develop an automated technique for student performance prediction. Existing studies on student performance prediction primarily focus on utilizing the conventional feature representation schemes, where extracted features are fed to a classifier. In recent years, deep learning has enabled researchers to automatically extract high-level features from raw data. Such advanced feature representation schemes enable superior performance in challenging tasks. In this work, we examine the deep neural network model, namely, the attention-based Bidirectional Long Short-Term Memory (BiLSTM) network to efficiently predict student performance (grades) from historical data. In this article, we have used the most advanced BiLSTM combined with an attention mechanism model by analyzing existing research problems, which are based on advanced feature classification and prediction. This work is really vital for academicians, universities, and government departments to early predict the performance. The superior sequence learning capabilities of BiLSTM combined with attention mechanism yield superior performance compared to the existing state-of-the-art. The proposed method has achieved a prediction accuracy of 90.16%.

Download Full-text