A topic sentiment based method for friend recommendation in online social networks via matrix factorization
Data sparsity and prediction quality have been recognized as the crucial challenges in recommender system. With the expansion of social network data, social network analysis is becoming more and more important. Traditional ...
3DSportNet: 3D sport reconstruction by quality-aware deep multi-video summation
Automatically reconstructing 3D sceneries from video sequences is an indispensable technique in computer 3D games, urban planning, and intelligent navigation. Many previous work relies on complicated and expensive equipment to fulfill ...
Analysis of active faults based on natural earthquakes in Central north China
As an important part of the integration of Beijing-Tianjin-Hebei, it is very important to analyze the seismic activity of active structures in Central north China. There are two sets of active faults belt in the lot, and there have ...
Visual tracking via dynamic weighting with pyramid-redetection based Siamese networks
- An improved end-to-end Siamese network for visual tracking algorithm.
- The ...
Siamese network based similarity-learning algorithm is currently a significant branch of visual tracking. However, most of existing deep Siamese networks depend much on the offline-trained knowledge and always assume the same ...
Intelligent attack defense scheme based on DQL algorithm in mobile fog computing
Fog computing is a technology that can expands the network computing mode of cloud computing and extends network computing from the network center to the network edge. It adds fog layer between cloud data center layer and Internet of ...
Image quality recognition technology based on deep learning
Image plays an important role in today's society and is an important information carrier. However, due to the problems in shooting or processing, image quality is often difficult to be guaranteed, and low-quality images are often ...
An extensive review on spectral imaging in biometric systems: Challenges & advancements
- Spectral imaging can aid visible imaging systems during identity recognition.
- ...
Spectral imaging has recently gained traction for face recognition in biometric systems. We investigate the merits of spectral imaging for face recognition and the current challenges that hamper the widespread deployment of spectral ...
Study on short-term network forecasting based on SVM-MFA algorithm
Accurate prediction of power supply load is vital in power industry, which provides economic operation decision for the power operation department. For the unpredictability and periodicity of power load, nonlinear intelligent ...
Generative image deblurring based on multi-scaled residual adversary network driven by composed prior-posterior loss
Conditional Generative Adversarial Networks (CGANs) have been introduced to generate realistic images from extremely degraded inputs. However, these generative models without prior knowledge of spatial distributions has limited ...
Egocentric visitors localization in natural sites
- A new egocentric dataset collected in a natural site for visitor localization purpose.
Localizing visitors in natural environments is challenging due to the unavailability of pre-installed cameras or other infrastructure such as WiFi networks. We propose to perform localization using egocentric images collected from the ...
Image quality study of CT imaging examination in children with childhood tumors under ultrasound-guided puncture
According to data released by the World Health Organization, malignant tumors have become the second leading cause of death among Chinese children. For malignant tumors, effective diagnostic information directly determines the ...
Scene categorization towards urban tunnel traffic by image quality assessment
Scene categorization is an indispensable technique in intelligent systems, such as scene parsing, video surveillance or autonomous driving. Considering traffic analysis under big data, in this paper, we propose scene categorization ...
Fusing dynamic deep learned features and handcrafted features for facial expression recognition
The automated recognition of facial expressions has been actively researched due to its wide-ranging applications. The recent advances in deep learning have improved the performance facial expression recognition (FER) methods. In this ...
An image denoising approach based on adaptive nonlocal total variation
- Our regularization parameter is adaptively determined according to the image content.
In the nonlocal total variation (NLTV) model the constant regularization parameter λ cannot adaptively control the balance between the regularization term and the fidelity term, which may results in over-smoothing and the more losing ...
Learning attentive dynamic maps (ADMs) for Understanding Human Actions
- Present an end-to-end trainable deep architecture to learn an attentive dynamic map (ADM).
This paper presents a novel end-to-end trainable deep architecture to learn an attentive dynamic map (ADM) for understanding human motion from skeleton data. An ADM intends not only to capture the dynamic information over the period of ...
Generation of personalized video summaries by detecting viewer’s emotion using electroencephalography
- Personalized video summarization framework based on human emotions is proposed.
Video summaries produced by low level features are unaware of the viewer’s requirements and result in a semantic gap. Video content evokes certain emotions in a viewer, which can be measured and act as a strong source of information to ...
Saliency detection using Multi-layer graph ranking and combined neural networks
- A combined net is proposed to improve salient object detection.
- An function is ...
In this paper, a new algorithm based on a combined neural network is proposed to improve salient object detection in the complex images. It consists of two main steps. The first step, an objective function which is optimized on a multi-...
Learning full-reference quality-guided discriminative gradient cues for lane detection based on neural networks
Learning an intelligent lane detection system is significant to autonomous vehicles, which is a crucial module to smart cars. Although conventional approaches have achieved impressive performance, they suffer from the following ...
Salient object detection based on novel graph model
In this paper, we present a salient object detection method based on novel graph structure. Given image is segmented into small image regions as basic units, we firstly construct an effective background-based map, each image region’s ...
An extensive evaluation of deep featuresof convolutional neural networks for saliency prediction of human visual attention
Based on transfer learning, feature maps of deep convolutional neural networks (DCNNs) have been used to predict human visual attention. In this paper, we conduct extensive comparisons to investigate effects of feature maps on the ...
Multisource surveillance video coding with synthetic reference frame
- Global knowledge contributes to the prediction of newly appeared regions of the objects.
Due to the increasing growth of surveillance data, high-efficiency surveillance video coding schemes are demanded. However, the existing conventional coding framework has difficulties in handling rotation and zooming whilst the ...
The affective facial recognition task: The influence of cognitive styles and exposure times
The main task of emotional facial recognition is to understand human emotion expression through the recognition of facial expressions, so as to achieve more effective communication and interpersonal communication. Therefore, facial ...
Quality-guided key frames selection from video stream based on object detection
Object detection technique is widely applied in modern intelligent systems, such as pedestrian tracking, video surveillance. Key frames selection aims to select more informative frames and reduce amount of redundant information frames. ...
Large-scale and adaptive service composition based on deep reinforcement learning
Service composition is a research hotspot with practical value. With the development of Web service, many Web services with the same functional attributes emerge. However, service composition optimization is still a big challenge since ...
Benchmarking deep learning techniques for face recognition
- Training networks for face recognition is very complex and time-consuming.
- ...
Recent progresses in Convolutional Neural Networks (CNNs) and GPUs have greatly advanced the state-of-the-art performance for face recognition. However, training CNNs for face recognition is complex and time-consuming. Multiple factors ...
Multiple object tracking in soccer videos using topographic surface analysis
- Adaptively using results of background subtraction and edge detection.
- Applying ...
Multiple object tracking is still a challenging problem in computer vision even though there have been several attempts lately to resolve the tracking problem in the framework of deep neural networks. In this paper, a novel method for ...
Application research of digital image technology in graphic design
With the development of the information age and the popularity of Internet computer technology, the application field of digital image technology has been further expanded. Digital image technology can not only buy the interchange of ...
Design of high-resolution quantization scheme with exp-Golomb code applied to compression of special images
Display Omitted
Highlights
- An adaptive quantization scheme based on the exp-Golomb code is proposed.
- The ...
For the compression of special image, such as medical image and aerial image, the reconstructed image quality is of utmost importance in the performance analysis. In this paper, a high-resolution quantization scheme based on the exp-...
