Search

Conventional methods for the early fusion of multi-modal features cannot recognize the relevant modality corresponding to the demand of each user in sequential recommendation. In this paper, we propose the adaptive multi-modal bidirectional long short-term memory network (AM-Bi-LSTM) to recognize the relevant modality for sequential recommendation. Specifically, we construct a new recurrent neural network model that is based on the bidirectional long short-term memory network and obtains multi-modal features, including each user’s sequential actions. Our new modality attention module calculates the importance degree of multi-modal features for sequential operations via the late-fusion approach, which results in the method recognizing the relevant modality. In experiments on a multi-modal and sequential dataset including 14,941 clicks constructed from the largest Web service for teachers in Japan, we demonstrate that AM-Bi-LSTM outperforms existing methods in terms of the diversity, explainability, and accuracy of recommendation. Specifically, we obtain Recall@10 that is 0.1005 better than that of existing early-fusion methods. Moreover, we obtain a value of catalog coverage@10 (representing diversity) that is 0.1710 higher than that for existing methods.

Decoding a person's cognitive contents from evoked brain activity is becoming important in the field of brain-computer interaction. Previous studies have decoded a perceived image from functional magnetic resonance imaging (fMRI) activity by constructing brain decoding models that were trained with a single subject's fMRI data. However, accurate decoding is still challenging since fMRI data acquired from only a single subject have several disadvantageous characteristics such as small sample size, noisy nature, and high dimensionality. In this article, we propose a method to decode categories of perceived images from fMRI activity using shared information of multi-subject fMRI data. Specifically, by aggregating fMRI data of multiple subjects that contain a large number of samples, we extract a low-dimensional latent representation shared by multi-subject fMRI data. Then the latent representation is nonlinearly transformed into visual features and semantic features of the perceived images to identify categories from various candidate categories. Our approach leverages rich information obtained from multi-subject fMRI data and improves the decoding performance. Experimental results obtained by using two public fMRI datasets showed that the proposed method can more accurately decode categories of perceived images from fMRI activity than previous approaches using a single subject's fMRI data.

A novel trial for estimating popularity of artists in music streaming services (MSS) is presented in this paper. The main contribution of this paper is to improve extensibility for using multi-modal features to accurately analyze latent relationships between artists. In the proposed method, a novel framework to construct a network is derived by collaboratively using social metadata and multi-modal features via canonical correlation analysis. Different from conventional methods that do not use multi-modal features, the proposed method can construct a network that can capture social metadata and multi-modal features, i.e., a context-aware network. For effectively analyzing the context-aware network, a novel framework to realize popularity estimation of artists is developed based on network analysis. The proposed method enables effective utilization of the network structure by extracting node features via a node embedding algorithm. By constructing an estimator that can distinguish differences between the node features, the proposed method can archive accurate popularity estimation of artists. Experimental results using multiple real-world datasets that contain artists in various genres in Spotify, one of the largest MSS, are presented. Quantitative and qualitative evaluations show that our method is effective for both classifying and regressing the popularity.

Although Twitter has become an important source of information, the number of accessible tweets is too large for users to easily find their desired information. To overcome this difficulty, a method for tweet clustering is proposed in this paper. Inspired by the reports that network representation is useful for multimedia content analysis including clustering, a network-based approach is employed. Specifically, a consensus clustering method for tweet networks that represent relationships among the tweets' semantics and sentiment are newly derived. The proposed method integrates multiple clustering results obtained by applying successful clustering methods to the tweet networks. By integrating complementary clustering results obtained based on semantic and sentiment features, the accurate clustering of tweets becomes feasible. The contribution of this work can be found in the utilization of the features, which differs from existing network-based consensus clustering methods that target only the network structure. Experimental results for a real-world Twitter dataset, which includes 65 553 tweets of 25 datasets, verify the effectiveness of the proposed method.

A novel method for music video recommendation is presented in this paper. The contributions of this paper are two-fold. (i) The proposed method constructs a network, which not only represents relationships between music videos and users but also captures multi-modal features of music videos. This enables collaborative use of multi-modal features such as audio, visual, and textual features, and multiple social metadata that can represent relationships between music videos and users on video hosting services. (ii) A novel scheme for link prediction considering local and global structures of the network (LP-LGSN) is newly derived by fusing multiple link prediction scores based on both local and global structures. By using the LP-LGSN to predict the degrees to which users desire music videos, the proposed method can recommend users’ desired music videos. The experimental results for a real-world dataset constructed from YouTube-8M show the effectiveness of the proposed method.

Sentiment in multimedia contents has an influence on their topics, since multimedia contents are tools for social media users to convey their sentiment. Performance of applications such as retrieval and recommendation will be improved if sentiment in multimedia contents can be estimated; however, there have been few works in which such applications were realized by utilizing sentiment analysis. In this paper, a novel method for extracting the hierarchical structure of Web video groups based on sentiment-aware signed network analysis is presented to realize Web video retrieval. First, the proposed method estimates latent links between Web videos by using multimodal features of contents and sentiment features obtained from texts attached to Web videos. Thus, our method enables construction of a signed network that reflects not only similarities but also positive and negative relations between topics of Web videos. Moreover, an algorithm to optimize a modularity-based measure, which can adaptively adjust the balance between positive and negative edges, was newly developed. This algorithm detects Web video groups with similar topics at multiple abstraction levels; thus, successful extraction of the hierarchical structure becomes feasible. By providing the hierarchical structure, users can obtain an overview of many Web videos and it becomes feasible to successfully retrieve the desired Web videos. Results of experiments using a new benchmark dataset, YouTube-8M, validate the contributions of this paper, i.e., 1) the first attempt to utilize sentiment analysis for Web video grouping and 2) a novel algorithm for analyzing a weighted signed network derived from sentiment and multimodal features.