Multimedia recommendation has received much attention in recent years. It models user preferences based on both behavior information and item multimodal information. Though current GCN-based methods achieve notable success, they suffer from two limitations: (1) Modality noise contamination to the item representations. Existing methods often mix modality features and behavior features in a single view (e.g., user-item view) for propagation, the noise in the modality features may be amplified and coupled with behavior features. In the end, it leads to poor feature discriminability; (2) Incomplete user preference modeling caused by equal treatment of modality features. Users often exhibit distinct modality preferences when purchasing different items. Equally fusing each modality feature ignores the relative importance among different modalities, leading to the suboptimal user preference modeling. To tackle the above issues, we propose a novel Multi-View Graph Convolutional Network (MGCN) for the multimedia recommendation. Specifically, to avoid modality noise contamination, the modality features are first purified with the aid of item behavior information. Then, the purified modality features of items and behavior features are enriched in separate views, including the user-item view and the item-item view. In this way, the distinguishability of features is enhanced. Meanwhile, a behavior-aware fuser is designed to comprehensively model user preferences by adaptively learning the relative importance of different modality features. Furthermore, we equip the fuser with a self-supervised auxiliary task. This task is expected to maximize the mutual information between the fused multimodal features and behavior features, so as to capture complementary and supplementary preference information simultaneously. Extensive experiments on three public datasets demonstrate the effectiveness of our methods. Our code is made publicly available on https://github.com/demonph10/MGCN.

In this paper, we introduce a new neonatal facial expression database for pain analysis. This database, called facial expression of neonatal pain (FENP), contains 11000 neonatal facial expression images associated with 106 Chinese neonates from two children's hospitals, i.e., the Children's Hospital Affiliated to Nanjing Medical University and Second Affiliated Hospital Affiliated to Nanjing Medical University in China. The facial expression images cover four categories of facial expressions, i.e., severe pain expression, mild pain expression, crying expression and calmness expression, where each category contains 2750 neonatal facial expression images. Based on this database, we also investigate the pain facial expression recognition problem using several state-of-the-art facial expression features and expression recognition methods, such as Gabor+SVM, LBP+SVM, HOG+SVM, LBP+HOG+SVM, and several Convolutional Neural Network (CNN) methods (including AlexNet, VGGNet, GoogLeNet, ResNet and DenseNet). The experimental results indicate that the proposed neonatal pain facial expression database would be very suitable for the study of both neonatal pain and facial expression recognition. Moreover, the FENP database would be publicly available after signing a license agreement (the users can contact Jingjie Yan (yanjingjie@njupt.edu.cn) or Guanming Lu (lugm@njupt.edu.cn)).

Micro-expression recognition (MER) holds significance in uncovering hidden emotions. Most works take image sequences as input and cannot effectively explore ME information because subtle ME-related motions are easily submerged in unrelated information. Instead, the facial landmark is a lowdimensional and compact modality, which achieves lower computational cost and potentially concentrates on ME-related movement features. However, the discriminability of facial landmarks for MER is unclear. Thus, this paper investigates the contribution of facial landmarks and proposes a novel framework to efficiently recognize MEs with facial landmarks. Firstly, a geometric twostream graph network is constructed to aggregate the low-order and high-order geometric movement information from facial landmarks to obtain discriminative ME representation. Secondly, a self-learning fashion is introduced to automatically model the dynamic relationship between nodes even long-distance nodes. Furthermore, an adaptive action unit loss is proposed to reasonably build a strong correlation between landmarks, facial action units and MEs. Notably, this work provides a novel idea with much higher efficiency to promote MER, only utilizing graphbased geometric features. The experimental results demonstrate that the proposed method achieves competitive performance with a significantly reduced computational cost. Furthermore, facial landmarks significantly contribute to MER and are worth further study for high-efficient ME analysis.

Facial image inpainting is a challenging task because the missing region needs to be filled by the new pixels with semantic information (e.g., noses and mouths). The traditional methods that involve searching for similar patches are mature but it is not suitable for semantic inpainting. Recently, the deep generative model-based methods have been able to implement semantic image inpainting although inpainting results are blurry or distorted. In this paper, through analyzing the advantages and disadvantages of the two methods, we propose a novel and efficient method that combines these two methods by a series connection, which searches for the most reasonable similar patch using the coarse image generated by the deep generative model. When training model, adding Laplace Loss to standard loss accelerates model convergence. In addition, we define Region Weight (RW) when searching for similar patches, which makes edge connection more natural. Our method addresses the problem of blurred results in the deep generative model and dissatisfactory semantic information in the traditional methods. Our experiments, which used the CelebA dataset, demonstrate that our method can achieve realistic and natural facial inpainting results.

With the development of researches on single image super-resolution (SISR) based on convolutional neural networks (CNN), the quality of recovered images has been remarkably promoted. Since then, many deep learning-based models have been proposed, which have outperformed the traditional SISR algorithms. According to the results of extensive experiments, the feature representations of the model can be enhanced by increasing the depth and width of the network, which can ultimately improve the image reconstruction quality. However, a larger network generally consumes more computational and memory resources, making it difficult to train the network and increasing the prediction time. In view of the above problems, a novel deeply-recursive low- and high-frequency fusing network (DRFFN) for SISR tasks is proposed in this paper, which adopts the structure of parallel branches to extract the low- and high-frequency information of the image, respectively. The different complexities of the branches can reflect the frequency characteristic of the diverse image information. Moreover, an effective channel-wise attention mechanism based on variance (VCA) is designed to make the information distribution of each feature map more reasonably with different variances. Owing to model structure (i.e., cascading recursive learning of recursive units), DRFFN and DRFFN-L are very compact, where the weights are shared by all convolutional recursions. Comprehensive benchmark evaluations in standard benchmark datasets well demonstrate that DRFFN outperforms the most existing models and has achieved competitive, quantitative, and visual results.