Parkinson's disease (PD) is a common degenerative disease of the nervous system in the elderly. The early diagnosis of PD is very important for potential patients to receive prompt treatment and avoid the aggravation of the disease. Recent studies have found that PD patients always suffer from emotional expression disorder, thus forming the characteristics of “masked faces”. Based on this, we thus propose an auto PD diagnosis method based on mixed emotional facial expressions in the paper. Specifically, the proposed method is cast into four steps: Firstly, we synthesize virtual face images containing six basic expressions ( i.e. , anger, disgust, fear, happiness, sadness, and surprise) via generative adversarial learning, in order to approximate the premorbid expressions of PD patients; Secondly, we design an effective screening scheme to assess the quality of the above synthesized facial expression images and then shortlist the high-quality ones; Thirdly, we train a deep feature extractor accompanied with a facial expression classifier based on the mixture of the original facial expression images of the PD patients, the high-quality synthesized facial expression images of PD patients, and the normal facial expression images from other public face datasets; Finally, with the well-trained deep feature extractor, we thus adopt it to extract the latent expression features for six facial expression images of a potential PD patient to conduct PD/non-PD prediction. To show real-world impacts, we also collected a new facial expression dataset of PD patients in collaboration with a hospital. Extensive experiments are conducted to validate the effectiveness of the proposed method for PD diagnosis and facial expression recognition.

Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed architecture has been widely used in correspondence to each single task. This may lead to the representation learned by the model being task-specific, and inevitably result in the lack of generalization ability of the feature based on multi-modal modeling. More recent studies have shown that establishing cross-modal relationship between auditory and visual stream is a promising solution for the challenge of audio-visual multi-task learning. Therefore, as a motivation to bridge the multi-modal associations in audio-visual tasks, a unified framework is proposed to achieve target speaker detection and speech enhancement with joint learning of audio-visual modeling in this study. With the assistance of audio-visual channels of videos in challenging real-world scenarios, the proposed method is able to exploit inherent correlations in both audio and visual signals, which is used to further anticipate and model the temporal audio-visual relationships across spatial-temporal space via a cross-modal conformer. In addition, a plug-and-play multi-modal layer normalization is introduced to alleviate the distribution misalignment of multi-modal features. Based on cross-modal circulant fusion, the proposed model is capable to learned all audio-visual representations in a holistic process. Substantial experiments demonstrate that the correlations between different modalities and the associations among diverse tasks can be learned by the optimized model more effectively. In comparison to other state-of-the-art works, the proposed work shows a superior performance for active speaker detection and audio-visual speech enhancement on three benchmark datasets, also with a favorable generalization in diverse challenges. Code is available at: https://github.com/Overcautious/ADENet.

Video-based abnormal driving behavior detection is becoming more and more popular for the time being, as it is highly important in ensuring safeties of drivers and passengers in the vehicle, and it is an essential step in realizing automatic driving at the current stage. Thanks to recent developments in deep learning techniques, this challenging detection task can be largely facilitated via the prominent generalization capability of sophisticated deep learning models as well as large volumes of video clips which are indispensable for thoroughly training these data-driven deep learning models. In this study, deep learning fusion techniques are emphasized, and three novel deep learning-based fusion models inspired by the recently proposed and popular densely connected convolutional network (DenseNet) are introduced, to fulfill the video-based abnormal driving behavior detection task for the first time. These three new deep learning-based fusion models are named as the wide group densely (WGD) network, the wide group residual densely (WGRD) network, and the alternative wide group residual densely (AWGRD) network, respectively. Technically, WGD takes important issues of deep learning models, i.e., the depth, the width and the cardinality, into consideration when designing its model structure based on DenseNet. For WGRD and AWGRD, they are more sophisticated as the important idea of residual networks with superpositions of previous layers is incorporated. Extensive experiments are conducted to verify the effectiveness of three new models. Their superiority has been suggested based on rigorous comparisons towards several popular deep learning models in this video-based abnormal driving behavior detection study.

Person-dependent facial expression recognition has received considerable research attention in recent years. Unfortunately, different identities can adversely influence recognition accuracy, and the recognition task becomes challenging. Other adverse factors, including limited training data and improper measures of facial expressions, can further contribute to the above dilemma. To solve these problems, a novel identity-aware method is proposed in this study. Furthermore, this study also represents the first attempt to fulfill the challenging person-dependent facial expression recognition task based on deep metric learning and facial image synthesis techniques. Technically, a StarGAN is incorporated to synthesize facial images depicting different but complete basic emotions for each identity to augment the training data. Then, a deep-convolutional-neural-network-based network is employed to automatically extract latent features from both real facial images and all synthesized facial images. Next, a Mahalanobis metric network trained based on extracted latent features outputs a learned metric that measures facial expression differences between images, and the recognition task can thus be realized. Extensive experiments based on several well-known publicly available datasets are carried out in this study for performance evaluations. Person-dependent datasets, including CK+, Oulu (all 6 subdatasets), MMI, ISAFE, ISED, etc., are all incorporated. After comparing the new method with several popular or state-of-the-art facial expression recognition methods, its superiority in person-dependent facial expression recognition can be proposed from a statistical point of view.

Recently, Graph Neural Networks (GNNs) have been widely used for fraud detection. GNNs first generate node embedding by aggregating neighboring information under different relations, and then use the final node embedding to detect the node’s suspiciousness. However, traditional GNNs employing only a single type of aggregator fail to capture neighbor information from multiple perspectives and treating different relations equally inevitably weakens the semantic information of heterogeneous graphs. Meanwhile, expressive ability of GNNs is limited by using conventional concatenating or averaging operations to update the center node. Also, camouflaged entities could damage GNN-based models. To handle these problems, a novel heterogeneous GNN model called Multiple Aggregators and Feature Interactions Network (MAFI) is proposed in this paper to conduct fraud detection tasks. Concretely, multiple types of aggregators are applied on different relations to aggregate neighbor information and aggregator-level attention is utilized to learn the importance of different aggregators. Also, relation-level attention is leveraged to learn the importance of each relation. Besides, conventional update operations are replaced with vector-wise implicit and explicit feature interactions. Moreover, a trainable neighbor sampler is employed to filter camouflaged fraudsters. Comprehensive experiments on two real-world fraud datasets indicate that the proposed MAFI outperforms existing GNN-based fraud detectors.