UbiShop: Commercial item recommendation using visual part-based object representation

With the popularity of online shopping, people have used to shop commercial items on the online shopping websites for convenience. However, based on traditional text search methods, people usually can not find the interesting commercial item they want if they do not know its detailed information, e.g., the name and the seller. Therefore, a more convenient method to help people find the commercial item they want is desired. In this work, we develop a practical system, UbiShop, on mobile phones, whereby users can timely get the related information of interesting commercial items by taking pictures of them. Users can also obtain recommendations on visually similar commercial items to help their buying selections. With the observation that people’s preferences on commercial items usually simply depend on their partial visual styles, we propose a novel representation, Visual Part-based Object Representation (VPOR), for commercial item images. The concept of VPOR is to decompose an item image into a set of disjointed partitions, with each of them represents a meaningful semantic parts. User can thus assign non-uniform preferences on the different parts of the commercial item to obtain a personalized recommended results. The experimental results verify our observation and show that the proposed VPOR based commercial item recommendation can achieve better performance than existing text-based and visual-based methods according to the user study.     

关联文本信息的网络表示学习推荐算法

通过基于随机游走的网络表示学习算法得到节点的低维嵌入向量,进而将其应用于推荐系统是推荐领域很流行的研究方向.针对当前基于随机游走的网络表示学习算法仅着重考虑了网络结构特性而忽略文本信息的问题,提出一种关联文本信息的网络表示学习推荐算法.首先在随机游走阶段,考虑到了节点文本间的相似度,联合结构和文本信息对下一游走节点进行...     

基于图卷积集成的网络表示学习

针对现有网络表示学习方法泛化能力较弱等问题,提出了将stacking集成思想应用于网络表示学习的方法,旨在提升网络表示性能。首先,将3个经典的浅层网络表示学习方法DeepWalk、Node2Vec、Line作为并列的初级学习器,训练得到三部分的节点嵌入拼接后作为新数据集;然后,选择图卷积网络(graph convolutional network, GCN)作为次级学习器对新数据集和网络结构进行stacking集成得到最终的节点嵌入,GCN处理半监督分类问题有很好的效果,因为网络表示学习具有无监督性,所以利用网络的一阶邻近性设计损失函数;最后,设计评价指标分别评价初级学习器和集成后的节点嵌入。实验表明,选用GCN集成的效果良好,各评价指标平均提升了1.47~2.97倍。     

Probabilistic visual learning for object representation

We present an unsupervised technique for visual learning, which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for unimodal distributions) and a mixture-of-Gaussians model (for multimodal distributions). Those probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition and coding. Our learning technique is applied to the probabilistic visual modeling, detection, recognition, and coding of human faces and nonrigid objects, such as hands     

Accurate visual representation learning for single object tracking

As a fundamental visual task, single object tracking has witnessed astonishing improvements. However, there still existing many factors should be to addressed for accurately tracking performance. Among them, visual representation is one of important influencers suffer from complex appearance changes. In this work, we propose a rich appearance representation learning strategy for tracking. First, by embedding the saliency feature extractor module, we try to improve the visual representation ability by fusing the saliency information learning from different convolution lays. With leveraging lightweight Convolutional Neural Network VGG-M as the features extractor backbone, we can attain robust appearance model by deep features with fruitful semantic information. Second, as for the classifier has significant complementary guidance for location prediction, we propose to generate diverse feature instances of the target by introducing the adversarial learning strategy. Given the generated diverse instances, many complex situations in the tracking process can be effectively simulated, especially the occlusion that conformed to the long tail distribution. Third, to optimize the bounding boxes refinement, we employ a precise pooling strategy for attaining feature maps with high resolution. Then, our approach can capture the subtle appearance changes effectively over a long time range. Finally, extensive experiments was conducted on several benchmark datasets, the results demonstrate that the proposed approach performs favorably against many state-of-the-art algorithms.

     

A real-time recommendation engine using lambda architecture

In a data science theory, the recommended methodology is one of the most popular theories and has been deployed in many real industries. However, one of the most challenging problems these days is how to recommend items with massively streaming data. Therefore, this paper aims to do a real-time recommendation engine using the Lambda architecture. The Apache Hadoop and Apache Spark frameworks were used in this research to process the MovieLens dataset comprised 100 K and 20 M ratings from the GroupLens research. Using alternating least squares (ALS) and k-means algorithms, the top K recommendation movies and the top K trending movies for each user were shown as results. Additionally, the mean squared error (MSE) and within cluster sum of squared error (WCSS) had been computed to evaluate the performance of the ALS and k-means algorithms, sequentially. The results showed that they are acceptable since the MSE and WCSS values are low when comparing to the size of data. However, they can still be improved by tuning some parameters.     

An attribute-based ant colony system for adaptive learning object recommendation

Teachers usually have a personal understanding of what “good teaching” means, and as a result of their experience and educationally related domain knowledge, many of them create learning objects (LO) and put them on the web for study use. In fact, most students cannot find the most suitable LO (e.g. learning materials, learning assets, or learning packages) from webs. Consequently, many researchers have focused on developing e-learning systems with personalized learning mechanisms to assist on-line web-based learning and to adaptively provide learning paths. However, although most personalized learning mechanism systems neglect to consider the relationship between learner attributes (e.g. learning style, domain knowledge) and LO’s attributes. Thus, it is not easy for a learner to find an adaptive learning object that reflects his own attributes in relationship to learning object attributes. Therefore, in this paper, based on an ant colony optimization (ACO) algorithm, we proposed an attributes-based ant colony system (AACS) to help learners find an adaptive learning object more effectively. Our paper makes three critical contributions: (1) It presents an attribute-based search mechanism to find adaptive learning objects effectively; (2) An attributes-ant algorithm was proposed; (3) An adaptive learning rule was developed to identify how learners with different attributes may locate learning objects which have a higher probability of being useful and suitable; (4) A web-based learning portal was created for learners to find the learning objects more effectively.     

A novel approach for high dimension 3D object representation using Multi-Mother Wavelet Network

In this paper, we present a novel approach for 3D objects representation. Our idea is to prove that wavelet networks are capable for reconstruction and representing irregular 3D objects used in computer graphics. The major contribution consist to transform an input surface vertices into signals and to provide instantaneously an estimation of the output values for input values. To prove this, we will use a new structure of wavelet network founded on several mother wavelet families. This structure uses several mother wavelet, in order to maximize best wavelet selection probability. An algorithm to construct this structure is presented. First, Data is taken from 3D object. The vertices and their corresponding normal values of a 3D object are used to create a training set. To this stage, the training set can be expressed according to three functions, which interpolates all their vertices. Second we approximate each function using wavelet network. To achieve a better approximation, the network is trained several iterations to optimize wavelet selection for every mother. To guarantee a small error criterion, we adjust wavelet network parameters (weight, translation and dilation) by using an improved Orthogonal Least Squares method version. We consider our proposed approach on some 3D examples to prove that the new approach is able to approximate 3D objects with a good approximation ability.     

Socialized healthcare service recommendation using deep learning

Socialized recommender system recommends reliable healthcare services for users. Ratings are predicted on the healthcare services by merging recommendations given by users who has social relations with the active users. However, existing works did not consider the influence of distrust between users. They recommend items only based on the trust relations between users. We therefore propose a novel deep learning-based socialized healthcare service recommender model, which recommends healthcare services with recommendations given by recommenders with both trust relations and distrust relations with the active users. The influences of recommenders, considering both the node information and the structure information, are merged via the deep learning model. Experimental results show that the proposed model outperforms the existing works on prediction accuracy and prediction coverage simultaneously, even for cold start users or users with very sparse trust relations. It is also computational less expensive.

     

Closed-loop object recognition using reinforcement learning

Current computer vision systems whose basic methodology is open-loop or filter type typically use image segmentation followed by object recognition algorithms. These systems are not robust for most real-world applications. In contrast, the system presented here achieves robust performance by using reinforcement learning to induce a mapping from input images to corresponding segmentation parameters. This is accomplished by using the confidence level of model matching as a reinforcement signal for a team of learning automata to search for segmentation parameters during training. The use of the recognition algorithm as part of the evaluation function for image segmentation gives rise to significant improvement of the system performance by automatic generation of recognition strategies. The system is verified through experiments on sequences of indoor and outdoor color images with varying external conditions     

基于多粒度结构的网络表示学习

图卷积网络（GCN）能够适应不同结构的图,但多数基于GCN的方法难以有效地捕获网络的高阶相似性。简单添加卷积层将导致输出特征过度平滑并使它们难以区分,而且深层神经网络更难训练。本文选择将网络的多粒度结构和图卷积网络结合起来用于学习网络的节点特征表示,提出基于多粒度结构的网络表示学习方法Multi-GS。首先,基于模块度聚类和粒计算思想,用分层递阶的多粒度空间替代原始的单层网络拓扑空间;然后,利用GCN模型学习不同粗细粒度空间中粒的表示;最后,由粗到细将不同粒的表示组合为原始空间中节点的表示。实验结果表明:Multi-GS能够捕获多种结构信息,包括一阶和二阶相似性、社团内相似性（高阶结构）和社团间相似性（全局结构）。在绝大多数情况下,使用多粒度的结构可改善节点分类任务的分类效果。     

基于物体坐标系的三维图形数据表示

鉴于世界坐标系定义的空间往往远大于被描绘物体的几何尺寸。导至了数据冗余、分辩率低、本文提出用物体坐标系表示三维图形，使存储空间减少，分辨率提高，并可提高运算速度。     

Salient object detection using content-sensitive hypergraph representation and partitioning

As an important problem in image understanding, salient object detection is essential for image classification, object recognition, as well as image retrieval. In this paper, we propose a new approach to detect salient objects from an image by using content-sensitive hypergraph representation and partitioning. Firstly, a polygonal potential Region-Of-Interest (p-ROI) is extracted through analyzing the edge distribution in an image. Secondly, the image is represented by a content-sensitive hypergraph. Instead of using fixed features and parameters for all the images, we propose a new content-sensitive method for feature selection and hypergraph construction. In this method, the most discriminant color channel which maximizes the difference between p-ROI and the background is selected for each image. Also the number of neighbors in hyperedges is adjusted automatically according to the image content. Finally, an incremental hypergraph partitioning is utilized to generate the candidate regions for the final salient object detection, in which all the candidate regions are evaluated by p-ROI and the best match one will be the selected as final salient object. Our approach has been extensively evaluated on a large benchmark image database. Experimental results show that our approach can not only achieve considerable improvement in terms of commonly adopted performance measures in salient object detection, but also provide more precise object boundaries which is desirable for further image processing and understanding.     

Binary object extraction using bi-directional self-organizing neural network (BDSONN) architecture with fuzzy context sensitive thresholding

A novel neural network architecture suitable for image processing applications and comprising three interconnected fuzzy layers of neurons and devoid of any back-propagation algorithm for weight adjustment is proposed in this article. The fuzzy layers of neurons represent the fuzzy membership information of the image scene to be processed. One of the fuzzy layers of neurons acts as an input layer of the network. The two remaining layers viz. the intermediate layer and the output layer are counter-propagating fuzzy layers of neurons. These layers are meant for processing the input image information available from the input layer. The constituent neurons within each layer of the network architecture are fully connected to each other. The intermediate layer neurons are also connected to the corresponding neurons and to a set of neighbors in the input layer. The neurons at the intermediate layer and the output layer are also connected to each other and to the respective neighbors of the corresponding other layer following a neighborhood based connectivity. The proposed architecture uses fuzzy membership based weight assignment and subsequent updating procedure. Some fuzzy cardinality based image context sensitive information are used for deciding the thresholding capabilities of the network. The network self organizes the input image information by counter-propagation of the fuzzy network states between the intermediate and the output layers of the network. The attainment of stability of the fuzzy neighborhood hostility measures at the output layer of the network or the corresponding fuzzy entropy measures determine the convergence of the network operation. An application of the proposed architecture for the extraction of binary objects from various degrees of noisy backgrounds is demonstrated using a synthetic and a real life image.

基于改进随机游走的网络表示学习算法

现有的基于Word2vec的网络表示学习（NRL）算法使用随机游走（RW）来生成节点序列,针对随机游走倾向于选择具有较大度的节点,生成的节点序列不能很好地反映网络结构信息,从而影响表示学习性能的问题,提出了基于改进随机游走的网络表示学习算法。首先,使用RLP-MHRW算法生成节点序列,它在生成节点序列时不会偏向大度节点,得到的节点序列能更好地反映网络结构信息;然后,将节点序列投入到Skip-gram模型得到节点表示向量;最后,利用链路预测任务来测度表示学习性能。在4个真实网络数据集上进行了实验。在论文合作网络arXiv ASTRO-PH上与LINE和node2vec算法相比,链路预测的AUC值分别提升了8.9%和3.5%,其他数据集上也均有提升。实验结果表明,RLP-MHRW能有效提高基于Word2vec的网络表示学习算法的性能。     

小样本条件下的RGB-D显著性物体检测

目的 现有基于RGB-D(RGB-depth)的显著性物体检测方法往往通过全监督方式在一个较小的RGB-D训练集上进行训练,因此其泛化性能受到较大的局限。受小样本学习方法的启发,本文将RGB-D显著性物体检测视为小样本问题,利用模型解空间优化和训练样本扩充两类小样本学习方法,探究并解决小样本条件下的RGB-D显著性物体检测。方法 模型解空间优化通过对RGB和RGB-D显著性物体检测这两种任务进行多任务学习,并采用模型参数共享的方式约束模型的解空间,从而将额外的RGB显著性物体检测任务学习到的知识迁移至RGB-D显著性物体检测任务中。另外,训练样本扩充通过深度估计算法从额外的RGB数据生成相应的深度图,并将RGB图像和所生成的深度图用于RGB-D显著性物体检测任务的训练。结果 在9个数据集上的对比实验表明,引入小样本学习方法能有效提升RGB-D显著性物体检测的性能。此外,对不同小样本学习方法在不同的RGB-D显著性物体检测模型下(包括典型的中期融合模型和后期融合模型)进行了对比研究,并进行相关分析与讨论。结论 本文尝试将小样本学习方法用于RGB-D显著性物体检测,探究并利用两种不同小样本...     

Multi-class object detection system using hybrid convolutional neural network architecture

Multimedia Tools and Applications - Object detection in computer vision has been a significant research area for the past decade. Identifying objects with multiple classes from an image has...