Search

Perfect image compositing can harmonize the appearance between the foreground and background effectively so that the composite result looks seamless and natural. However, the traditional convolutional neural network (CNN)-based methods often fail to yield highly realistic composite results due to overdependence on scene parsing while ignoring the coherence of semantic and structural between foreground and background. In this paper, we propose a framework to solve this problem by training a stacked generative adversarial network with attention guidance, which can efficiently create a high-resolution, realistic-looking composite. To this end, we develop a diverse adversarial loss in addition to perceptual and guidance loss to train the proposed generative network. Moreover, we construct a multi-scenario dataset for high-resolution image compositing, which contains high-quality images with different styles and object masks. Experiments on the synthesized and real images demonstrate the efficiency and effectiveness of our network in producing seamless, natural, and realistic results. Ablation studies show that our proposed network can improve the visual performance of composite results compared with the application of existing methods.

Feature engineering usually needs to excavate dense-and-implicit cross features from multi-filed sparse data. Recently, many state-of-the-art models have been proposed to achieve low-order and high-order feature interactions. However, most of them ignore the importance of cross features and fail to suppress the negative impact of useless features. In this paper, a novel multi-scale feature-crossing attention network (MsFcNET) is proposed to extract dense-and-implicit cross features and learn their importance in the different scales. The model adopts the DIA-LSTM units to construct a new attention calibration architecture, which can adaptively adjust the weights of features in the process of feature interactions. On the other hand, it also integrates a multi-scale feature-crossing module to strengthen the representation ability of cross features from multi-field sparse data. The extensive experimental results on three real-world prediction datasets demonstrate that our proposed model yields superior performance compared with the other state-of-the-art models.

A number of edge-aware filters can efficiently boost the appearance of an image by detail decomposition and enhancement. However, they often fail to produce photographic enhanced appearance due to some visible artifacts, especially noise, halos and unnatural contrast. The essential reason is that the guidance and the constraint of high-quality appearance are not sufficient enough in the process of enhancement. Thus our idea is to train a detail dictionary from a lot of high-quality patches in order to constrain and control the entire appearance enhancement. In this paper, we propose a novel learningbased enhancement method for photographic appearance, which includes two main stages: dictionary training and sparse reconstruction. In the training stage, we construct a training set of detail patches extracted from some high-quality photos, and then train an overcomplete detail dictionary by iteratively minimizing an l 1-norm energy function. In the reconstruction stage, we employ the trained dictionary to reconstruct the boosted detail layer, and further formalize a gradient-guided optimization function to improve the local coherence between patches. Moreover, we propose two evaluation metrics to measure the performance of appearance enhancement. The final experimental results have demonstrated the effectiveness of our learning-based enhancement method.

Cigarette code is a string printed on the wrapper of cigarette packet as a basis of distinguishing illegal sales for tobacco administration. In general, the code is excerpted and entered to administration system manually during on-site inspection, which is quite time-consuming and laborious. In this paper, we propose a new solution based on convolutional neural network for intelligent transcription. Our recognition method is composed of four components: detection, identification, alignment, and regularization. First of all, the detection component fine-tunes an end-to-end detection network to obtain the bounding box region of cigarette code. Then the identification component constructs an optimized CNN architecture to recognize each character in the region of cigarette code. Meanwhile the alignment component trains a CPM-based network to estimate the positions of all characters including some missing characters. Finally, the regularization component develops a matching algorithm to produce a regularized result with all characters. The experimental results demonstrate that our proposed method can perform a better, faster and more labor-saving cigarette code transcription process.

China film market has become the second largest box office market just after North America today, the Chinese film market is less than 1/5 size of the now, in 10 years ago. The Chinese film market is growing so fast, the reasons research on this phenomenon become a hot spot. In this article, we tried to find the rule of films box office market based on the historical data of China released film. Gaining film market rules will help film-makers understand audience preferences and make decisions on future movie projects. We collected the movies data released in China in recent 15 years which contains box office, and basic information (such as release date, language, type, country, etc.), correspondingly, we also collected the movie audience's com-ments on the internet, more than 100000 comments in total, There is no public movies released in China set provided by a inde-pendent agency until now, According to the obtained data, we analyzed the movies data distribution rules in the month, year, genre, using language, We also visualized the proportion of all films in the rating (from douban.com), and analyzed collectively the quality of domestic released films. We conducted word cloud processing on the comments of the highest box office movie Wolf warriors 2, which demonstrate intuitively the public's discussion on this movie.

This paper presents a Class-C LC VCO which can be used for 802.11 b/g/n, Bluetooth and ZigBee. Implemented in 0.18μm process, the VCO can achieve coarse frequency tuning and fine frequency tuning. The bias voltage of the cross-coupled transistors can be adjusted to control the conduction angle of the VCO to improve the current utilization efficiency. The bias current can be adjusted to achieve a compromise of power consumption and phase noise.

Face aging is one of research hotspots in the field of computer vision, but there is no mature system yet that can be applied to digital entertainment. This paper proposes a face aging system based on feature fusion, which can synthesize aging facial images of young people efficiently and quickly by using facial texture features of elderly people's facial images, achieve the goal of simulating the appearance after aging. The system published online by the “eleme” app for the Mother's Day, showing great potential for digital entertainment.

Face anti-spoofing, as a security measure for face verification and recognition system, could distinguish between genuine and fake faces. Although some impressive results have been achieved by CNN when evaluated on intra-tests (i.e. the model is trained and tested on the same dataset). Unfortunately, most of these models fail to generalize well to unseen attacks (e.g. when the model is trained on one dataset and then evaluated on another dataset). This is a major concern in face anti-spoofing research which is mostly overlooked. Our experiments on two challenging benchmark face spoofing datasets, CASIA and Replay-Attack, demonstrate the disappointed adaptation ability for CNN from one dataset to another. Via visualizing the implicit attention of CNN, we find that scene-dependent features extracted by CNN affect models generalization capabilities. To address this problem, we propose a novel solution based on applying scene-independent features representation.

Video facial swap usually has strong entertainment applications, and it is also applicable for the post-production of films and has great application value. At present, the popular face swap is done manually by the PS software, and the synthetic effect of the automatic face changing technology is not good. In order to make up for the lack of these features, this paper proposes a method of video face swap based on autoencoder generation network. The network learns the mapping relationship between distorted face and original face: the encoder can distinguish and extract facial information, and the decoder can restore face separately. First, the local information of tow face is sent to the network to get the initial model; then, the global information is put into the network for fine-tuning; finally, the face exchange between A and B is completed with face alignment and alpha fusion. The experimental results show that the quality of the method is improved significantly.

A 125 KHz wake-up receiver to receive wake-up signal and a 433MHz data transmitter to transmit temperature and pressure data of the tire to central control module for battery-less TPMS (Tire Pressure Monitoring System) are presented in this paper. The receiver adopts dual-channel to improve reliability and logarithmic amplifier to achieve ASK demodulation and dynamic range compression. The receiver is implemented in 0.35μm BCD process. Maximum data rate is 35Kbps with 0.5mVpp sensitivity and 5μA typical power consumption. The transmitter is implemented in 0.18μm process. The typical power consumption is 7.3mA with a transmit power of −10 dBm@433.9 MHz, and phase noise of the PLL is − 103dBc/Hz@ 300 KHz with 30Kbps data rate.

High dynamic range (HDR) imaging has seen a lot of progress in recent years, while an efficient way to capture and generate HDR video is still in need. In this paper, we present a method to generate HDR video from frame sequence of alternating exposures in a fast and concise fashion. It takes advantage of the recent advancement in deep learning to achieve superior efficiency compared to other state-of-art method. By training an end-to-end CNN model to estimate optical flow between frames of different exposures, we are able to achieve dense image registration of them. Using this as a base, we develop an efficient method to reconstruct the aligned LDR frames with different exposure and then merge them to produce the corresponding HDR frame. Our approach shows good performance and time efficiency while still maintain a relatively concise framework.

Tone mapping can compress the color range of HDR (high dynamic range) image to produce its LDR (low dynamic range) image. However, without preserving the original scene detail, tone mapping may produce various artifacts and their fidelity will be severely decreased. In this paper, we propose a new detail-preserving refinement method to efficiently improve the fidelity of tone mapping. Its overall flow includes the four key steps: tone initialization, detail extraction, tone reconstruction, and detail restoration. First of all, we employ clustering and decomposition to obtain initial tone layer and detail map. Then we construct detail affinity and gradient guidance to optimize the detail map and reconstruct the new tone layer. Finally, we combine them to produce a high-fidelity result of tone mapping. We demonstrate the effectiveness of the proposed method through a number of experiments in visual comparison, and verify its high-efficiency performance in execution time.

A 130 nm 1Mb embedded phase change memory (PCM) has been achieved, requiring only three additional masks for phase change storage element, featuring 500 kb/s single channel write throughput and > 10 8 endurance. The prepare process has been optimized to reduce the cost and power. An 80 nm heat electrode has been prepared with 130 nm process. The optimal Read/Write circuit module is designed to realize the load/store function for PCM. The critical operation parameter is Reset/70 ns/2.5 mA and Set/1500 ns/1 mA, which means that the signal channel write throughput arrives to 500 kb/s.

In order to reduce the RESET current of phase change memory (PCM), which is fabricated using standard 0.13-μm CMOS technology, we have investigated various process factors that might affect the phase transition process, including doping concentration, diameter of bottom electrode contact (BEC) and different chalcogenide materials. Test results suggest that the PCM memory cell, utilizing Si2Sb2Te5 (SST) material as storage element with 80 nm BEC, can be operated using a 40 ns electrical pulse with current amplitude as small as 0.5 mA. This is mainly resulted from the high electrical resistances of the novel chalcogenide both in amorphous and crystalline state, which contribute greatly to the improved efficiency of heating process.

In this paper, a real-time facial animation system is presented, that captures live facial expressions and poses from user, and uses them to animate a synthetic 2.5D cartoon character (Avatar) in real-time. Compared to existing 3D Avatar systems, the 2.5D cartoon models are easier to create than full 3D model, and the cartoon-style drawings are more popular among young people. Our system requires only an ordinary PC camera, and the initialization is fully automatic. We established a mapping from real-time facial motion to the atomic motion parameters of the cartoon model by pose and expression estimation. The animation is driven by these parameters in the way of blend shape interpolation.

Generally, for a global or local color transfer, the traditional approaches will rearrange color distribution in source image according to reference image. However, the destruction of scene detail and illumination environment might produce a low-fidelity color transfer result. In this paper, we propose a unified fidelity optimization model for color transfer to yield a high-fidelity transfer result in terms of color, detail and illumination. Corresponding to the three characteristics, our approach is described as an optimization problem with three energy terms: color mapping, detail preserving and illumination awareness. Color mapping can employ histogram matching to impose the color style of reference image on source image; Detail preserving can apply gradient guidance to maintain scene detail in source image; Illumination awareness can construct illumination affinity to harmonize illumination environment. Moreover, following the definition of fidelity with three characteristics, we also propose an objective evaluation metric to analyze the performance of our approach in different coefficients. The comparison of experiment results demonstrates the effectiveness of our optimization model.

In order to organise the awareness information in the collaborative learning environment reasonably and efficiently, making good use of the ontology characteristics such as clear knowledge organization, explicit definition of concept and relation etc, an awareness ontology model is presented in this paper. The model contains six aspects: person, community, role, KnowledgeDomain, event and activity as well as each kind of relations among these concepts and in the concept interior. This model can solve the existing flaws like chaotic organization and difficult maintenance in the traditional mode of awareness information organization. Thus enhances collaborative learning efficiency in the greatest degree. For constructing needed ontology reasonably and conveniently, a method of KnowledgeDomain correlativity extraction based on the N-Grams is presented on the basis of awareness ontology model. It can extract the asrelativity? relation automatically and satisfy dynamic awareness processing

We report the analysis and TCAD results of a gate-all-around cylindrical (GAAC) FinFET with operation based on channel accumulation. The cylindrical channel of the GAAC FinFET is essentially controlled by an infinite number of gates surrounding the cylinder-shaped channel. The symmetrical nature of the field in the channel leads to improved electrical characteristics, e.g. reduced leakage current and negligible corner effects. The Ion/Ioff ratio of the device can be larger than 10 6 , as the key parameter for device operation. The GAAC FinFET operating in