In recent years, depression, as a serious mental illness, has received widespread attention from various sectors of society. How to identify depressive emotions in a timely manner and detect depression has become an u...
详细信息
Infrared videos often suffer from low contrast and insufficient texture. In order to improve poor visual effect, a novel infrared video enhancement method is proposed, which contains intra-frame brightness enhancement...
详细信息
An abdominal CT liver tumor segmentation algorithm based on three-channel cascade SEU-Nets and C-LSTM is proposed in this paper. Concerning the accuracy of most known algorithms is limited by using single-phase CT ima...
详细信息
In view of the fact that the proportion of face in the whole image is small and the face posture is skew, which leads to the low accuracy of facial expression recognition, this paper proposes a two-branch neural netwo...
详细信息
Dual-energy CBCT imaging plays a crucial role in advanced imaging applications due to its ability to quantify material components. Although there are multiple established systems for dual-energy imaging, they often co...
详细信息
The application of CBCT systems in intraoperative environments has become increasingly common, but concurrent CBCT systems are unsuitable for situations that require a large longitudinal imaging FoV, such as orthopedi...
详细信息
作者：
Tong, ZhanWu, ZhanYang, YangMao, WeilongWang, ShijieLi, YinshengChen, YangSoutheast University
Laboratory of Image Science and Technology Nanjing210096 China Southeast University
Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Chinese Academy of Sciences
Research Center for Medical Artificial Intelligence Shenzhen Institutes of Advanced Technology Shenzhen518055 China School of Computer Science and Engineering
Key Lab. of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology Nanjing210096 China
Computed Tomography (CT) is an imaging technique widely used in clinical diagnosis. However, high-attenuation metallic implants result in the obstruction of low-energy Xrays and further lead to metal artifacts in the ...
详细信息
In this work, we proposed a bidirectional attention-aware fluid pyramid features integrated fusion network (BAF-Net) with cross-modal interactions for multi-modality medical images prognosis. The network is composed o...
详细信息
In order to improve the behavior of the prognostic model for patients with head and neck cancer (HNC), we constructed a graph convolutional network (GCN), characterizing the interaction of functional and structural in...
详细信息
Face sketch-photo synthesis aims at generating a facial photo conditioned on a given photo. It has attracted wide attention in computer vision and has been widely applied in law enforcement and entertainment. However,...
详细信息
ISBN:
(纸本)9781665450867
Face sketch-photo synthesis aims at generating a facial photo conditioned on a given photo. It has attracted wide attention in computer vision and has been widely applied in law enforcement and entertainment. However, precisely synthesizing high-quality face photos is still challenging due to the missing color information in face sketches. To alleviate the problem, we propose an attribute and Semantic constrained Generative Adversarial Networks (ASGAN), which introduces face attribute and semantic constraints to improve the quality and accuracy of synthesized photos. Specifically, We first annotate the key attributes in the dataset and form a 14-dimensional attribute vector for each face. Then, the attribute features and semantic features obtained by face parsing are fused. Finally, the generator takes the fused constrain features and sketches as input and constructs two-stream encoders to synthesize high-quality photos. Extensive experimental results demonstrate that our method can significantly outperform state-of-the-art methods. It can synthe-size higher-quality face photos while maintaining the identity, attributes, and structure. Meanwhile, it can alleviate the problem of background and skin color synthesis errors.
暂无评论