Search

Currently, attention mechanisms are widely used in aspect-level sentiment analysis tasks. Previous studies have only used attention mechanisms combined with neural networks for aspect-level sentiment classification, and the feature extraction of the model is insufficient. When the same aspect and sentiment polarity appear in multiple sentences, the semantic information sharing of the same domain is also ignored, resulting in low model performance. To address these problems, the paper proposes an aspect-level sentiment analysis model, GCAT-GTCU, which combines a Graph-connected Attention Network containing symmetry with Gate Than Change Unit. Three nodes of words, sentences, and aspects are constructed, and local and deep-level features of sentences are extracted using CNN splicing BiGRU; node connection information is added to GAT to form a GCAT containing symmetry to realize the information interaction of three nodes, pay attention to the contextual information, and update the shared information of three nodes at any time; a new gating mechanism GTCU is constructed to filter noisy information and control the flow of sentiment information; finally, the three nodes are extracted information to predict the final sentiment polarity. The experimental results on four publicly available datasets show that the model outperforms the baseline model against which it is compared in some very controlled situations. [ABSTRACT FROM AUTHOR]

In recommendation tasks, we model user preferences by learning node representations (i.e., user and item embeddings) based on the observed user-item interaction data, which is a bipartite graph. Graph Neural Networks (GNNs) are widely used to refine the representations by exploring the topology of the graph: embeddings of neighbors are propagated to each node to reconstruct its embeddings. However, the propagation strategy in existing GNNs is empirical and defective: (1) a substantial proportion of links are missed in the sparse observed graph, which causes ineffective and biased propagation; and (2) the propagation weights are determined by a coarse pre-defined rule, which only takes the degree of nodes into consideration. In this paper, we propose a dense and data-driven propagation mechanism for GNNs. Considering the graph we use to propagate embeddings in recommendation tasks is extremely sparse, we complement it and use the predicted graph as the new propagation tool. We learn the propagation matrix from the data, and propose a Self-propagation Graph Neural Network (SGNN). Since it is very space- and time-consuming to maintain a large and dense propagation matrix, we factorize it for storing and updating. In this paper, we propose three methods to complete the sparse graph and construct the propagation matrix: (1) we complete the graph based on a recommendation model; (2) we measure the node distance based on spectral clustering; (3) we predict missing links of the graph based on predictive embeddings. In SGNN, the embeddings can be propagated to not only the observed neighbors, but also the potential yet unobserved neighbors, and the propagation weights are learned based on the connection strength. Comprehensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of our proposed model: SGNN outperforms recent state-of-the-art GNNs significantly. Codes are available on https://github.com/Wenhui-Yu/LCFN. [ABSTRACT FROM AUTHOR]

At present, most mainstream algorithms for single image super-resolution (SISR) assume the image degradation process as an ideal degradation process (e.g. bicubic downscaling), which violates the actual degeneration conditions. In real-world image capturing, objects often move in a dynamic environment, and camera shake also often occurs, which results in serious blurs. Our work focuses on the task of image super-resolution with heavy motion blur, for which we adopt a network with two branches: one branch for image deblurring and the other one for super-resolution. Since the features obtained by the deblurring are rich in details, we apply their features as supplementary information to the super-resolution branch. Based on the adopted dual-branch framework, our major technical novelties lie in two novel modules: Multi-Scale Feature Fusion (MSFF1) module which fuses features of different scale from the deblurring branch to get local and global information, and Multi-Stage Feature Fusion (MSFF2) module which further filters useful information with attention. We evaluate the proposed method under various blur scenarios on the benchmark datasets, demonstrating competitive performance against existing methods. [ABSTRACT FROM AUTHOR]

A content recommendation system based on human brain activity has become a reality. However, the cost of collecting the information from people is problematic. This article proposes a scheme that resolves the tradeoff between the inference performance from a profile model to a brain model and the cost of collecting profile information. In the proposed scheme, a machine learning model infers the brain model from the profile model and a feature selection method is applied to reduce the cost, i.e., the number of questionnaire items, of collecting profile information. Since only the top questionnaire items with the highest importance scores are used, we can maintain the inference performance as high as possible while limiting the number of questionnaire items. We demonstrate the effectiveness of the proposed scheme with a performance evaluation using an experimentally obtained brain model and a profile model created from real profile information. The results over different experimental parameters, video lengths, and feature selection methods demonstrate that the proposed scheme successfully identifies the top questionnaire items that contribute most significantly to the inference of brain models. [ABSTRACT FROM AUTHOR]

Knowledge graph exploration is an interactive knowledge discovery process over the knowledge graph. Entity recommendation deals with the information overflow issue when exploring the large-scale unfamiliar knowledge graphs. The traditional personalized entity recommendation methods for knowledge graph explorations rarely consider the adaptive topic-oriented long-term positive- and negative intent modeling. In this article, we propose a topic-oriented entity recommendation method during the knowledge graph exploration. We build a negative feedback memory network model for obtaining the user's long-term negative intents. We propose a transformer-based sequence encoder for the positive intents. We dynamically obtain the adaptive intents by aggregating the positive- and negative intents by the proposed intent attention mechanism. Experiments show that our method has advantages in TopK entity recommendations. [ABSTRACT FROM AUTHOR]

The graph-based hyperspectral image classification (HSIC) method has attracted wide attention because it can extract information with a non-Euclidean structure. Many graph-based HSIC works have achieved good results, but unresolved technical issues remain. For example, many graph nodes lead to high computational costs, and the mining of non-Euclidean structures is not sufficient. To solve these problems, we propose a graph attention network with an adaptive graph structure mining (GAT-AGSM) approach. Specifically, we first propose an HSIC framework with a superpixel feature subdivision (SFS) mechanism. In this framework, the number of nodes in the graph structure is reduced by using superpixel segmentation algorithms, and the SFS mechanism is designed to generate finer classification results. Second, we design the spatial–spectral attention layer with an adaptive graph structure mining (AGSM) mechanism for the graph attention network. The spatial–spectral attention layer can filter information in both spatial and spectral dimensions. The AGSM mechanism requires less manual intervention to dynamically generate non-Euclidean graph structures that better aggregate information. We conduct excessive experiments to compare the proposed GAT-AGSM with seven nongraph methods and three graph-based methods on widely used datasets. On the Indian Pines, Pavia University, and Salinas datasets, compared to the comparison method, the overall accuracy of GAT-AGSM is improved by at least 4.26%, 2.59%, and 1.41%, respectively. Experimental results show that GAT-AGSM has the best performance compared to the baselines in terms of various metrics. [ABSTRACT FROM AUTHOR]

Action repetition counting is to estimate the occurrence times of the repetitive motion in one action, which is a relatively new, significant, but challenging problem. To solve this problem, we propose a new method superior to the traditional ways in two aspects, without preprocessing and applicable for arbitrary periodicity actions. Without preprocessing, the proposed model makes our scheme convenient for real applications; processing the arbitrary periodicity action makes our model more suitable for the actual circumstance. In terms of methodology, firstly, we extract action features using ConvNets and then use Principal Component Analysis algorithm to generate the intuitive periodic information from the chaotic high-dimensional features; secondly, we propose an energy-based adaptive feature mode selection scheme to adaptively select proper deep feature mode according to the background of the video; thirdly,we construct the periodic waveform of the action based on the high-energy rules by filtering the irrelevant information. Finally, we detect the peaks to obtain the times of the action repetition. Our work features two-fold: 1) We give a significant insight that features extracted by ConvNets for action recognition can well model the self-similarity periodicity of the repetitive action. 2) A high-energy based periodicity mining rule using features from ConvNets is presented, which can process arbitrary actions without preprocessing. Experimental results show that our method achieves superior or comparable performance on the three benchmark datasets, i.e. YT_Segments, QUVA, and RARV. [ABSTRACT FROM AUTHOR]

In the task of person re-identification, the attention mechanism and fine-grained information have been proved to be effective. However, it has been observed that models often focus on the extraction of features with strong discrimination, and neglect other valuable features. The extracted fine-grained information may include redundancies. In addition, current methods lack an effective scheme to remove background interference. Therefore, this paper proposes the feature refinement and filter network to solve the above problems from three aspects: first, by weakening the high response features, we aim to identify highly valuable features and extract the complete features of persons, thereby enhancing the robustness of the model; second, by positioning and intercepting the high response areas of persons, we eliminate the interference arising from background information and strengthen the response of the model to the complete features of persons; finally, valuable fine-grained features are selected using a multi-branch attention network for person re-identification to enhance the performance of the model. Our extensive experiments on the benchmark Market-1501, DukeMTMC-reID, CUHK03 and MSMT17 person re-identification datasets demonstrate that the performance of our method is comparable to that of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. Thanks to the increasing availability of pre-trained image and video convolutional neural network models, deep visual features are widely used for video content representation. However, as how two videos are relevant is task-dependent, such off-the-shelf features are not always optimal for all tasks. Moreover, due to varied concerns including copyright, privacy and security, one might have access to only pre-computed video features rather than original videos. We propose in this paper feature re-learning for improving video relevance prediction, with no need of revisiting the original video content. In particular, re-learning is realized by projecting a given deep feature into a new space by an affine transformation. We optimize the re-learning process by a novel negative-enhanced triplet ranking loss. In order to generate more training data, we propose a new data augmentation strategy which works directly on frame-level and video-level features. Extensive experiments in the context of the Hulu Content-based Video Relevance Prediction Challenge 2018 justify the effectiveness of the proposed method and its state-of-the-art performance for content-based video relevance prediction. [ABSTRACT FROM AUTHOR]

Cloud-based visualization services have made visual analytics accessible to a much wider audience than ever before. Systems such as Tableau have started to amass increasingly large repositories of analytical knowledge in the form of interactive visualization workbooks. When shared, these collections can form a visual analytic knowledge base. However, as the size of a collection increases, so does the difficulty in finding relevant information. Content-based recommendation (CBR) systems could help analysts in finding and managing workbooks relevant to their interests. Toward this goal, we focus on text-based content that is representative of the subject matter of visualizations rather than the visual encodings and style. We discuss the challenges associated with creating a CBR based on visualization specifications and explore more concretely how to implement the relevance measures required using Tableau workbook specifications as the source of content data. We also demonstrate what information can be extracted from these visualization specifications and how various natural language processing techniques can be used to compute similarity between workbooks as one way to measure relevance. We report on a crowd-sourced user study to determine if our similarity measure mimics human judgement. Finally, we choose latent Dirichl et al.ocation (LDA) as a specific model and instantiate it in a proof-of-concept recommender tool to demonstrate the basic function of our similarity measure. [ABSTRACT FROM AUTHOR]

Most previous work on outfit recommendation focuses on designing visual features to enhance recommendations. Existing work neglects user comments of fashion items, which have been proven to be effective in generating explanations along with better recommendation results. We propose a novel neural network framework, neural outfit recommendation (NOR), that simultaneously provides outfit recommendations and generates abstractive comments. Neural outfit recommendation (NOR) consists of two parts: outfit matching and comment generation. For outfit matching, we propose a convolutional neural network with a mutual attention mechanism to extract visual features. The visual features are then decoded into a rating score for the matching prediction. For abstractive comment generation, we propose a gated recurrent neural network with a cross-modality attention mechanism to transform visual features into a concise sentence. The two parts are jointly trained based on a multi-task learning framework in an end-to-end back-propagation paradigm. Extensive experiments conducted on an existing dataset and a collected real-world dataset show NOR achieves significant improvements over state-of-the-art baselines for outfit recommendation. Meanwhile, our generated comments achieve impressive ROUGE and BLEU scores in comparison to human-written comments. The generated comments can be regarded as explanations for the recommendation results. We release the dataset and code to facilitate future research. [ABSTRACT FROM AUTHOR]

Food recommender systems play an important role in assisting users to identify the desired food to eat. Deciding what food to eat is a complex and multi-faceted process, which is influenced by many factors such as the ingredients, appearance of the recipe, the user's personal preference on food, and various contexts like what had been eaten in the past meals. This work formulates the food recommendation problem as predicting user preference on recipes based on three key factors that determine a user's choice on food, namely, 1) the user's (and other users’) history; 2) the ingredients of a recipe; and 3) the descriptive image of a recipe. To address this challenging problem, this work develops a dedicated neural network-based solution Hierarchical Attention based Food Recommendation (HAFR) which is capable of: 1) capturing the collaborative filtering effect like what similar users tend to eat; 2) inferring a user's preference at the ingredient level; and 3) learning user preference from the recipe's visual images. To evaluate our proposed method, this work constructs a large-scale dataset consisting of millions of ratings from AllRecipes.com. Extensive experiments show that our method outperforms several competing recommender solutions like Factorization Machine and Visual Bayesian Personalized Ranking with an average improvement of 12%, offering promising results in predicting user preference on food. [ABSTRACT FROM AUTHOR]

Event recommendation is an essential means to enable people to find attractive upcoming social events, such as party, exhibition, and concert. While growing line of research has focused on suggesting events to individuals, making event recommendation for a group of users has not been well studied. In this paper, we aim to recommend upcoming events for a group of users. We formalize group recommendation as a ranking problem and propose a group event recommendation framework GERF based on learning-to-rank technique. Specifically, we first analyze different contextual influences on user's event attendance, and extract preference of user to event considering each contextual influence. Then, the preference scores of the users in a group are taken as the features for learning-to-rank to model the preference of the group. Moreover, a fast pairwise learning-to-rank algorithm, Bayesian group ranking, is proposed to learn ranking model for each group. Our framework is easily to incorporate additional contextual influences, and can be applied to other group recommendation scenarios. Extensive experiments have been conducted to evaluate the performance of GERF on two real-world datasets and demonstrate the appealing performance of our method on both accuracy and time efficiency. [ABSTRACT FROM AUTHOR]