Search

Session-based recommendation (SBR) has drawn increasingly research attention in recent years, due to its great practical value by only exploiting the limited user behavior history in the current session. Existing methods typically learn the session embedding at the item level, namely, aggregating the embeddings of items with or without the attention weights assigned to items. However, they ignore the fact that a user's intent on adopting an item is driven by certain factors of the item (e.g., the leading actors of an movie). In other words, they have not explored finer-granularity interests of users at the factor level to generate the session embedding, leading to sub-optimal performance. To address the problem, we propose a novel method called Disentangled Graph Neural Network (Disen-GNN) to capture the session purpose with the consideration of factor-level attention on each item. Specifically, we first employ the disentangled learning technique to cast item embeddings into the embedding of multiple factors, and then use the gated graph neural network (GGNN) to learn the embedding factor-wisely based on the item adjacent similarity matrix computed for each factor. Moreover, the distance correlation is adopted to enhance the independence between each pair of factors. After representing each item with independent factors, an attention mechanism is designed to learn user intent to different factors of each item in the session. The session embedding is then generated by aggregating the item embeddings with attention weights of each item's factors. To this end, our model takes user intents at the factor level into account to infer the user purpose in a session. Extensive experiments on three benchmark datasets demonstrate the superiority of our method over existing methods.

In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS.

Fashion Compatibility Modeling (FCM), which aims to automatically evaluate whether a given set of fashion items makes a compatible outfit, has attracted increasing research attention. Recent studies have demonstrated the benefits of conducting the item representation disentanglement towards FCM. Although these efforts have achieved prominent progress, they still perform unsatisfactorily, as they mainly investigate the visual content of fashion items, while overlooking the semantic attributes of items (e.g., color and pattern), which could largely boost the model performance and interpretability. To address this issue, we propose to comprehensively explore the visual content and attributes of fashion items towards FCM. This problem is non-trivial considering the following challenges: a) how to utilize the irregular attribute labels of items to partially supervise the attribute-level representation learning of fashion items; b) how to ensure the intact disentanglement of attribute-level representations; and c) how to effectively sew the multiple granulairites (i.e, coarse-grained item-level and fine-grained attribute-level) information to enable performance improvement and interpretability. To address these challenges, in this work, we present a partially supervised outfit compatibility modeling scheme (PS-OCM). In particular, we first devise a partially supervised attribute-level embedding learning component to disentangle the fine-grained attribute embeddings from the entire visual feature of each item. We then introduce a disentangled completeness regularizer to prevent the information loss during disentanglement. Thereafter, we design a hierarchical graph convolutional network, which seamlessly integrates the attribute- and item-level compatibility modeling, and enables the explainable compatibility reasoning. Extensive experiments on the real-world dataset demonstrate that our PS-OCM significantly outperforms the state-of-the-art baselines. We have released our source codes and well-trained models to benefit other researchers (https://site2750.wixsite.com/ps-ocm).

In an effort to reduce environmental pollution and energy consumption, the Chinese government strongly promotes the usage of electric vehicles. However, studies focusing on assessing consumers’ willingness to pay (WTP) for electric vehicles (EVs) are limited in the country. This research aims to address this research gap by examining influencing factors of consumers’ WTP for EVs in the Chinese perspective. Combined with the existing consumers’ intention factors, the current study further contributed by augmenting the theoretical framework of the Theory of Planned Behavior by including three new dimensions (performance expectancy, information loaded, and perceived risk) to comprehensively analyze the willingness of Chinese consumers. Analysis is performed on survey data from 498 consumers using EVs in Beijing, China. To evaluate formulated hypotheses, structural equation modeling approach is employed. Empirical findings reveal that environmental knowledge and performance expectancy positively and significantly influence behavioral intention. In contrast, overloaded information has a negative impact on behavioral intention. Moreover, subjective norms are significantly and positively related to behavioral intention. The research outcomes further disclose that perceived risk is positively and significantly related to behavioral intention. Finally, behavioral intention has a significant and positive association with WTP for EVs. The study contributes to the literature on sustainable consumption behavior and provides academics and practitioners with essential future directions.

Green innovation is a significant component of high-value growth closely linked to China’s 14th five-year plan. This research investigates the influence of green innovation on the market performance of small- and medium-sized enterprises (SMEs). The results are based on the primary data gathered via an online questionnaire survey from 453 respondents working for SMEs in China. The structural equation modeling approach is used for data analysis purposes. The research findings highlight that green innovation positively impacts marketing and products. In turn, marketing innovation positively influences product innovation and market performance, and product innovation also significantly boosts market performance. The study’s findings lead us to suggest that organizations in developing countries should focus on SMEs’ green innovation, which will support them in achieving an effective market performance. The study’s limitations are noted so the findings can be interpreted with caution, and directions for future research are outlined for all stakeholders.

GWI survey 1 has highlighted the flourishing use of multiple social networks: the average number of social media accounts per Internet user is 5.54, and among them, 2.82 are being used actively. Indeed, users tend to express their views in more than one social media site. Hence, merging social signals of the same user across different social networks together, if available, can facilitate the downstream analyses. Previous work has paid little attention on modeling the cooperation among the following factors when fusing data from multiple social networks: 1) as data from different sources characterizes the characteristics of the same social user, the source consistency merits our attention; 2) due to their different functional emphases, some aspects of the same user captured by different social networks can be just complementary and results in the source complementarity; and 3) different sources can contribute differently to the user characterization and hence lead to the different source confidence. Toward this end, we propose a novel unified model, which co-regularizes source consistency, complementarity, and confidence to boost the learning performance with multiple social networks. In addition, we derived its theoretical solution and verified the model with the real-world application of user interest inference. Extensive experiments over several state-of-the-art competitors have justified the superiority of our model. 1 http://tinyurl.com/zk6kgc9

Temporal action localization is currently an active research topic in computer vision and machine learning due to its usage in smart surveillance. It is a challenging problem since the categories of the actions must be classified in untrimmed videos and the start and end of the actions need to be accurately found. Although many temporal action localization methods have been proposed, they require substantial amounts of computational resources for the training and inference processes. To solve these issues, in this work, a novel temporal-aware relation and attention network (abbreviated as TRA) is proposed for the temporal action localization task. TRA has an anchor-free and end-to-end architecture that fully uses temporal-aware information. Specifically, a temporal self-attention module is first designed to determine the relationship between different temporal positions, and more weight is given to features within the actions. Then, a multiple temporal aggregation module is constructed to aggregate the temporal domain information. Finally, a graph relation module is designed to obtain the aggregated graph features, which are used to refine the boundaries and classification results. Most importantly, these three modules are jointly explored in a unified framework, and temporal awareness is always fully used. Extensive experiments demonstrate that the proposed method can outperform all state-of-the-art methods on the THUMOS14 dataset with an average mAP that reaches 67.6% and obtain a comparable result on the ActivityNet1.3 dataset with an average mAP that reaches 34.4%. Compared with A2Net (TIP20), PCG-TAL (TIP21), and AFSD (CVPR21) TRA can achieve improvements of 11.7%, 4.4%, and 1.8%, respectively on the THUMOS14 dataset.

The objective of crowd counting is to learn a counter that can estimate the number of people in a single image. So far, most of the proposed work evaluates the crowd density by fitting the constructed density map corresponding to the sample. The performance of those algorithms depends on a large amount of carefully prepared data. However, a significant problem with crowd data sets is the difficulty of labeling. To address such a situation, utilizing object counting data in few‐shot scenes is considered and an efficient algorithm to extract the meta‐information is proposed, thus improving the accuracy and convergence rate of the crowd counting tasks. Specifically, the counting network is trained with only object counting tasks constructed on different domains during the meta‐training phase. Then, the meta‐counter is testing on crowd counting tasks in the meta‐testing stage. Experimentally, it is demonstrated that the above way improves the converge rate and accuracy of crowd counting tasks on three crowd counting datasets when meta‐training on ten‐type object counting tasks.

The prevailing characteristics of micro-videos result in the less descriptive power of each modality. The micro-video representations, several pioneer efforts proposed, are limited in implicitly exploring the consistency between different modality information but ignore the complementarity. In this paper, we focus on how to explicitly separate the consistent features and the complementary features from the mixed information and harness their combination to improve the expressiveness of each modality. Toward this end, we present a neural multimodal cooperative learning (NMCL) model to split the consistent component and the complementary component by a novel relation-aware attention mechanism. Specifically, the computed attention score can be used to measure the correlation between the features extracted from different modalities. Then, a threshold is learned for each modality to distinguish the consistent and complementary features according to the score. Thereafter, we integrate the consistent parts to enhance the representations and supplement the complementary ones to reinforce the information in each modality. As to the problem of redundant information, which may cause overfitting and is hard to distinguish, we devise an attention network to dynamically capture the features which closely related the category and output a discriminative representation for prediction. The experimental results on a real-world micro-video dataset show that the NMCL outperforms the state-of-the-art methods. Further studies verify the effectiveness and cooperative effects brought by the attentive mechanism.

In industrial enterprises, effective retrieval of three-dimensional (3-D) computer-aided design (CAD) models can greatly save time and cost in new product development and manufacturing, thus, many researchers have focused on it. Recently, many view-based 3D model retrieval methods have been proposed and have achieved state-of-the-art performance. However, most of these methods focus on extracting more discriminative view-level features and effectively aggregating the multi-view images of a 3D model, and the latent relationship among these multi-view images is not fully explored. Thus, we tackle this problem from the perspective of exploiting the relationships between patch features to capture long-range associations among multi-view images. To capture associations among views, in this work, we propose a novel patch convolutional neural network (PCNN ) for view-based 3D model retrieval. Specifically, we first employ a CNN to extract patch features of each view image separately. Second, a novel neural network module named PatchConv is designed to exploit intrinsic relationships between neighboring patches in the feature space to capture long-range associations among multi-view images. Then, an adaptive weighted view layer is further embedded into PCNN to automatically assign a weight to each view according to the similarity between each view feature and the view-pooling feature. Finally, a discrimination loss function is employed to extract the discriminative 3D model feature, which consists of softmax loss values generated by the fusion classifier and the specific classifier. Extensive experimental results on two public 3D model retrieval benchmarks, namely, the ModelNet40, and ModelNet10, demonstrate that our proposed PCNN can outperform state-of-the-art approaches, with mAP values of 93.67%, and 96.23%, respectively.

Person reidentification (ReID) is a very hot research topic in machine learning and computer vision, and many person ReID approaches have been proposed; however, most of these methods assume that the same person has the same clothes within a short time interval, and thus their visual appearance must be similar. However, in an actual surveillance environment, a given person has a great probability of changing clothes after a long time span, and they also often take different personal belongings with them. When the existing person ReID methods are applied in this type of case, almost all of them fail. To date, only a few works have focused on the cloth-changing person ReID task, but since it is very difficult to extract generalized and robust features for representing people with different clothes, their performances need to be improved. Moreover, visual-semantic information is often ignored. To solve these issues, in this work, a novel multigranular visual-semantic embedding algorithm (MVSE) is proposed for cloth-changing person ReID, where visual semantic information and human attributes are embedded into the network, and the generalized features of human appearance can be well learned to effectively solve the problem of clothing changes. Specifically, to fully represent a person with clothing changes, a multigranular feature representation scheme (MGR) is employed to focus on the unchanged part of the human, and then a cloth desensitization network (CDN) is designed to improve the feature robustness of the approach for the person with different clothing, where different high-level human attributes are fully utilized. Moreover, to further solve the issue of pose changes and occlusion under different camera perspectives, a partially semantically aligned network (PSA) is proposed to obtain the visual-semantic information that is used to align the human attributes.

As one of the most successful recommendation techniques, collaborative filtering provides a useful recommendation by associating an active user with a crowd of users who share the same interests. Although some achievements have been achieved both in theory and practice, the efficiency of recommender systems has been negatively affected by the problems of cold start and data sparsity recently. To solve the above problems, the trust relationship among users is employed into recommender systems to build a learning model to further promote the prediction quality and users’ satisfaction. However, most of the existing social networks-based recommendation algorithms fail to take into account the fact that users with different levels of trust and backgrounds, that is, user’s social status and homophily have different degrees of influence on their friends. In this paper, a novel social matrix factorization-based recommendation method is proposed to improve the recommendation quality by fusing user’s social status and homophily. User’s social status and homophily play important roles in improving the performance of recommender systems. We first build a user’s trust relationship network based on user social relationships and the rating information. Then, the degree of trust is calculated through the trust propagation method and the PageRank algorithm. Finally, the trust relationship is integrated into the matrix factorization model to accurately predict unknown ratings. The proposed method is evaluated using real-life datasets including the Epinions and Douban datasets. The experimental results and comparisons demonstrate that the proposed approach is superior to the existing social networks-based recommendation algorithms.

This study used a 2 × 2 experimental design to explore the effects of message type (non-narrative vs. narrative information) and social media metrics (high vs. low numbers of plays) of low-carbon-themed social media short videos on people’s willingness to protect the environment. Subjects completed questionnaires after viewing short videos that contained different message types and social media metrics, and a final sample of 295 cases was included in the data analysis. The study found that, while the type of information (i.e., non-narrative or narrative) of the low-carbon-themed social media short videos had no direct effect on people’s willingness to protect the environment, its indirect effects were significant. These indirect effects were achieved through immersion experience and social influence. Subjects who watched narrative videos had a higher level of immersion experience, which in turn was significantly and positively correlated with environmental intention; meanwhile, those who watched non-narrative videos experienced a higher level of social influence, which in turn was significantly and positively correlated with environmental intention. In addition, subjects who viewed high-volume videos experienced a more positive effect on their willingness to protect the environment. This study explored how message design could promote subjects’ perceptions and positive attitudes towards environmental protection, with important managerial implications.

Action recognition is a popular research topic in the computer vision and machine learning domains. Although many action recognition methods have been proposed, only a few researchers have focused on cross-domain few-shot action recognition, which must often be performed in real security surveillance. Since the problems of action recognition, domain adaptation, and few-shot learning need to be simultaneously solved, the cross-domain few-shot action recognition task is a challenging problem. To solve these issues, in this work, we develop a novel end-to-end pairwise attentive adversarial spatiotemporal network ( PASTN ) to perform the cross-domain few-shot action recognition task, in which spatiotemporal information acquisition, few-shot learning, and video domain adaptation are realised in a unified framework. Specifically, the Resnet-50 network is selected as the backbone of the PASTN , and a 3D convolution block is embedded in the top layer of the 2D CNN (ResNet-50) to capture the spatiotemporal representations. Moreover, a novel attentive adversarial network architecture is designed to align the spatiotemporal dynamics actions with higher domain discrepancies. In addition, the pairwise margin discrimination loss is designed for the pairwise network architecture to improve the discrimination of the learned domain-invariant spatiotemporal feature. The results of extensive experiments performed on three public benchmarks of the cross-domain action recognition datasets, including SDAI Action I , SDAI Action II and UCF50-OlympicSport, demonstrate that the proposed PASTN can significantly outperform the state-of-the-art cross-domain action recognition methods in terms of both the accuracy and computational time. Even when only two labelled training samples per category are considered in the office1 scenario of the SDAI Action I dataset, the accuracy of the PASTN is improved by 6.1%, 10.9%, 16.8%, and 14% compared to that of the $TA^{3}N$ , TemporalPooling, I3D, and P3D methods, respectively.

Automatic image captioning is to conduct the cross-modal conversion from image visual content to natural language text. Involving computer vision (CV) and natural language processing (NLP), it has become one of the most sophisticated research issues in the artificial-intelligence area. Based on the deep neural network, the neural image caption (NIC) model has achieved remarkable performance in image captioning, yet there still remain some essential challenges, such as the deviation between descriptive sentences generated by the model and the intrinsic content expressed by the image, the low accuracy of the image scene description, and the monotony of generated sentences. In addition, most of the current datasets and methods for image captioning are in English. However, considering the distinction between Chinese and English in syntax and semantics, it is necessary to develop specialized Chinese image caption generation methods to accommodate the difference. To solve the aforementioned problems, we design the NICVATP2L model via visual attention and topic modeling, in which the visual attention mechanism reduces the deviation and the topic model improves the accuracy and diversity of generated sentences. Specifically, in the encoding phase, convolutional neural network (CNN) and topic model are used to extract visual and topic features of the input images, respectively. In the decoding phase, an attention mechanism is applied to processing image visual features for obtaining image visual region features. Finally, the topic features and the visual region features are combined to guide the two-layer long short-term memory (LSTM) network for generating Chinese image captions. To justify our model, we have conducted experiments over the Chinese AIC-ICC image dataset. The experimental results show that our model can automatically generate more informative and descriptive captions in Chinese in a more natural way, and it outperforms the existing image captioning NIC model.

Distantly-supervised relation extraction has proven to be effective to find relational facts from texts. However, the existing approaches treat labels as independent and meaningless one-hot vectors, which cause a loss of potential label information for selecting valid instances. In this paper, we propose a novel multi-layer attention-based model to improve relation extraction with joint label embedding. The model makes full use of both structural information from Knowledge Graphs and textual information from entity descriptions to learn label embeddings through gating integration while avoiding the imposed noise with an attention mechanism. Then the learned label embeddings are used as another atten- tion over the instances (whose embeddings are also enhanced with the entity descriptions) for improving relation extraction. Extensive experiments demonstrate that our model significantly outperforms state-of-the-art methods.

Analyze the restrictive factors of Internet of things major in the curriculum system in according with present market demand situation of Internet of things talent. It is suggested that practice be combined with theory. Students' practice ability should be improved. Diverse curriculum should be created and a new training mode and training objective should be established to improve teaching effect of Internet of things major curriculum. 1. Background Internet of things technology can promote commercial profit. Internet of things and cloud computing are regarded as important direction of computer network, having great market value. At present, America, EU, Japan and other developed countries are having made detail plans in Internet of things talent cultivation and gradually make it come true. Meanwhile, to adapt to the market demand, China also devotes greater effort in education, renewing educational concept. It requires that vocational education combine with industry development. And the program is updated in the process of development. Strengthen corresponding major training to prepare for the social talent transformation. Setting up corresponding courses makes it easier for the learners to find correct position, to meet the demand of Internet of things market.

With the rapid development of science and technology, and better living standard of people, Internet having features of low cost, large information source and rapid speed, plays an important role in common people's life. Internet brings a lot of convenience while at the same time it causes series of social problems. Under the new situation, teen Internet addiction index is higher and higher. To solve Internet addiction problem needs every side to intervene.