Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent no-reference (NR-IQA) methods have made great progress to predict image quality free from the reference image, they still have the potential to achieve better performance since HQ image information is not fully exploited. In contrast, full-reference (FR-IQA) methods tend to provide more reliable quality evaluation, but its practicability is affected by the requirement for pixel-level aligned reference images. To address this, we firstly propose the content-variant reference method via knowledge distillation (CVRKD-IQA). Specifically, we use non-aligned reference (NAR) images to introduce various prior distributions of high-quality images. The comparisons of distribution differences between HQ and LQ images can help our model better assess the image quality. Further, the knowledge distillation transfers more HQ-LQ distribution difference information from the FR-teacher to the NAR-student and stabilizing CVRKD-IQA performance. Moreover, to fully mine the local-global combined information, while achieving faster inference speed, our model directly processes multiple image patches from the input with the MLP-mixer. Cross-dataset experiments verify that our model can outperform all NAR/NR-IQA SOTAs, even reach comparable performance than FR-IQA methods on some occasions. Since the content-variant and non-aligned reference HQ images are easy to obtain, our model can support more IQA applications with its robustness to content variations. Our code is available: https://github.com/guanghaoyin/CVRKD-IQA.

DEtection TRansformer (DETR) has achieved great success in object detection but suffers from slow convergence during training process. Knowledge distillation (KD) can speed up model training but has the problem of locating knowledgeable regions in object detection. Related methods mainly locate knowledgeable regions empirically. To address those challenges, we propose a novel distillation framework for DETR-like transformer-based detectors. The key idea is to connect each instance with its corresponding response region in the feature map through cross attention. To better fuse the attention maps between different queries and heads, we introduce an attention fusion module to balance instances of different scales. Extensive experiments on DETR and Conditional DETR are conducted to verify our proposed method. Our method improves the mAP by 3.19% for Conditional DETR with ResNet-50 backbone trained for 50 epochs, which outperforms the strong teacher trained for 108 epochs. We also boost DETR with ResNet-50 backbone from 33.97% to 42.13% mAP (+8.16%) under 50 epochs.

Although the single-image super-resolution (SISR) methods have achieved great success on the single degradation, they still suffer performance drop with multiple degrading effects in real scenarios. Recently, some blind and non-blind models for multiple degradations have been explored. However, these methods usually degrade significantly for distribution shifts between the training and test data. Towards this end, we propose a novel conditional hyper-network framework for super-resolution with multiple degradations (named CMDSR), which helps the SR framework learn how to adapt to changes in the degradation distribution of input. We extract degradation prior at the task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet). Specifically, the ConditionNet of our framework first learns the degradation prior from a support set, which is composed of a series of degraded image patches from the same task. Then the adaptive BaseNet rapidly shifts its parameters according to the conditional features. Moreover, in order to better extract degradation prior, we propose a task contrastive loss to shorten the inner-task distance and enlarge the cross-task distance between task-level features. Without predefining degradation maps, our blind framework can conduct one single parameter update to yield considerable improvement in SR results. Extensive experiments demonstrate the effectiveness of CMDSR over various blind, and even several non-blind methods. The flexible BaseNet structure also reveals that CMDSR can be a general framework for a large series of SISR models. Our code is available at https://github.com/guanghaoyin/CMDSR.

Considerable attention has been paid to physiological signal-based emotion recognition in the field of affective computing. For reliability and user-friendly acquisition, electrodermal activity (EDA) has a great advantage in practical applications. However, EDA-based emotion recognition with large-scale subjects is still a tough problem. The traditional well-designed classifiers with hand-crafted features produce poorer results because of their limited representation abilities. And the deep learning models with auto feature extraction suffer the overfitting drop-off because of large-scale individual differences. Since music has a strong correlation with human emotion, static music can be involved as the external benchmark to constrain various dynamic EDA signals. In this article, we make an attempt by fusing the subject’s individual EDA features and the external evoked music features. And we propose an end-to-end multimodal framework, the one-dimensional residual temporal and channel attention network (RTCAN-1D). For EDA features, the channel-temporal attention mechanism for EDA-based emotion recognition is first involved in mine the temporal and channel-wise dynamic and steady features. The comparisons with single EDA-based SOTA models on DEAP and AMIGOS datasets prove the effectiveness of RTCAN-1D to mine EDA features. For music features, we simply process the music signal with the open-source toolkit openSMILE to obtain external feature vectors. We conducted systematic and extensive evaluations. The experiments on the current largest music emotion dataset PMEmo validate that the fusion of EDA and music is a reliable and efficient solution for large-scale emotion recognition.

User independent emotion recognition with large scale physiological signals is a tough problem. There exist many advanced methods but they are conducted under relatively small datasets with dozens of subjects. Here, we propose Res-SIN, a novel end-to-end framework using Electrodermal Activity(EDA) signal images to classify human emotion. We first apply convex optimization-based EDA (cvxEDA) to decompose signals and mine the static and dynamic emotion changes. Then, we transform decomposed signals to images so that they can be effectively processed by CNN frameworks. The Res-SIN combines individual emotion features and external emotion benchmarks to accelerate convergence. We evaluate our approach on the PMEmo dataset, the currently largest emotional dataset containing music and EDA signals. To the best of author's knowledge, our method is the first attempt to classify large scale subject-independent emotion with 7962 pieces of EDA signals from 457 subjects. Experimental results demonstrate the reliability of our model and the binary classification accuracy of 73.65% and 73.43% on arousal and valence dimension can be used as a baseline.

Music can trigger human emotion. This is a psychophysiological process. Therefore, using psychophysiological characteristics could be a way to understand individual music emotional experience. In this study, we explore a new method of personal music emotion recognition based on human physiological characteristics. First, we build up a database of features based on emotions related to music and a database based on physiological signals derived from music listening including EDA, PPG, SKT, RSP, and PD variation information. Then linear regression, ridge regression, support vector machines with three different kernels, decision trees, k -nearest neighbors, multi-layer perceptron, and Nu support vector regression (NuSVR) are used to recognize music emotions via a data synthesis of music features and human physiological features. NuSVR outperforms the other methods. The correlation coefficient values are 0.7347 for arousal and 0.7902 for valence, while the mean squared errors are 0.023 23 for arousal and 0.014 85 for valence. Finally, we compare the different data sets and find that the data set with all the features (music features and all physiological features) has the best performance in modeling. The correlation coefficient values are 0.6499 for arousal and 0.7735 for valence, while the mean squared errors are 0.029 32 for arousal and 0.015 76 for valence. We provide an effective way to recognize personal music emotional experience, and the study can be applied to personalized music recommendation.

In the development of a new product, the design team must describe the expected effects of the final products to potential users and stakeholders. However, existing prototyping tools can only present a product imperfectly, due to limitations at different levels. Specifically, the physical product model, which may be the product of 3D printing, could lack a visual interface; the presentation of the product through modeling software such as Rhinoceros 3D does not provide good realistic tactile perception; or the interface platforms, such as Axure RP, used to display the interactive effects differ from those to be used in the actual operation. Thus, we present the VPModel, a high-fidelity prototyping tool, able to integrate multiple prototyping methods simultaneously. It combines a touchable 3D-printed product model (3DPM) and a corresponding visualized virtual model, and the interactive interfaces are rendered synchronously in a mixed-reality device. Through the tangible, visual, and interactive demonstration, designers and normal users can each obtain a similar experience to the experience of the finished product. Furthermore, the VPModel also enhances design practices by enabling comparisons between modular models. However, the implementation of this system is a challenging task, which subsumes several fundamental problems as sub-tasks: object detection, real-time matching, hand-gesture detection and action recognition. To achieve the expected goals of the VPModel, this system uses physical hardware (a Microsoft MR HoloLens headset, a Leap Motion Controller, and a 3D printer) and existing machine learning algorithms. To evaluate our VPModel, we report the user experience of 16 participants, evaluated using a closed-ended questionnaire survey, a quantitative analysis of task performance, and a qualitative analysis of open-ended interviews. The results show a significant improvement in realism and enjoyment using the VPModel over the two traditional camera prototype approaches. In summary, the VPModel can be used to support design strategy and to convey design concepts fully and efficiently, which indicates a potential use for the VPModel in shortening product development cycles and reducing communication costs.

Knowledge graph embedding significantly promotes the performance of link prediction and knowledge reasoning, which aims to encode both entities and relations into a low-dimensional semantic space. Existing translation-based methods have achieved state-of-art performances. However, the diversity of connectivity patterns observed in knowledge graph, i.e., structural equivalences, may not be effectively utilized to enhance knowledge graph embedding. To address this issue, we propose a concise but effective model, Context-enhanced Knowledge Graph Embedding (CKGE), for joint knowledge base embedding with neighborhood context. Neighborhood context obtained in our approach gain a deep insight into the diversity of connectivity patterns of knowledge graph. We incorporate the rich structural information contained in neighborhood context to expand the semantic structure of the knowledge graph, which is enable to model complex relations more precisely. We conduct extensive experiments on link prediction, triplet classification on bench-mark datasets. The experiment results show CKGE achieve significant improvements against the baseline methods.

To promote the development of the intangible cultural heritage of the world, shadow play, many studies have focused on shadow puppet modeling and interaction. Most of the shadow puppet figures are still imaginary, spread by ancients, or carved and painted by shadow puppet artists, without consideration of real dimensions or the appearance of human bodies. This study proposes an algorithm to transform 3D human models to 2D puppet figures for shadow puppets, including automatic location of feature points, automatic segmentation of 3D models, automatic extraction of 2D contours, automatic clothes matching, and animation. Experiment proves that more realistic and attractive figures and animations of the shadow puppet can be generated in real time with this algorithm.

A product image survey and retrieval model is constructed by the method of Kansei engineering. And a product image survey and retrieval system (PISR system) based on Kansei engineering is built according to this model, which is consisted of the product image survey subsystem and the product image retrieval subsystem. The online survey is carried out on Internet and then the product Kansei image based on consumers is extracted through various data analysis methods, according to the result of data analysis, a picture of 2D or 3D image scale is produced and it is convenient to obtain the information of product Kansei image for the designers, the product Kansei image databases are built and the designers can search the matching products by inputting image words as a reference, which makes designers and the consumers reach an agreement on product Kansei image. The application of the PISR system is universal to all kinds of products. It is successfully verified that this system can help the designers gain product orientation, conduct the process of product design and improve the overall efficiency of product development.

This paper proposes fractal strokes, to make fractal computation as controllable as ink. A fractal stroke is a skeletal stroke that recursively copies, recolors and distorts its neighboring image and then paint on the canvas. Fractal strokes can generate self-similar textures. On one hand, the general visual attributes of a stroke are decided by the user. On the other hand, a stroke's fine details depend on its context. Many modifications can easily been made so that fractal strokes can probably generate various new results beyond the scope of traditional artistic techniques.

We developed a simple system for designing 2D cloth patches, and converted 2D cloth patches to 3D garment by virtual seaming. By using the technique of parameterized human body modeling, virtual try-on was realized with the different shape of human body to the style and size of garment. Finally, integrating the techniques of character animation, physically based cloth simulation and non-precise deformable object collision handling, we create the real-time simulation animation of virtual human body wearing garment.

The purpose of the paper is to present a novel way to building Quantitative structure-retention relationship (QSRR) models. Studies was reported for predicting the retention times (RTs) of 110 pesticides which were detected by gas chromatography (GC) with mass selective detector (MSD). Chemical descriptors were calculated from the molecular structure of pesticides and the QSRR models of RTs with descriptors was built using the heuristic method (HM) and Improved Gene Expression Programming (IGEP), respectively. The obtained linear model of HM had a correlation coefficient R2 = 0.913, with a root mean square error (RMS) S2 of 0.0387 for the training set, while R2 =0.907, and RMS =0.0408 for the test set. The nonlinear model by IGEP gave better results: for the training set R2 = 0.971, S2 = 0.0176 and for the test set R2 =0.951, S2 =0.0267. The prediction results from nonlinear model are in agreement with the experimental values The QSRR model also reveals that the gas chromatographic RTs are associated with physicochemical property of pesticides.

Toward the limitations of existing MICE systems, a solution of interactive MICE systems is proposed. This paper explains the framework and the coordination mechanisms of the interactive MICE systems, then analyses the key technologies applied to the MICE systems, including data mining, humanistic interactive, 3D data transmit, and finally introduces the development and implementation of our MICE demo system

Cooperative design between users and designers is one of the most important research items in modern design. Well cooperation between users and designers can get better products in less time. In this research some users' image cognition experiment researches were taken to obtain users' image about automobiles. And product image cognition model based on random sets and the product image feature lines - imprecise concept creating technology had been applied to establish a prototype system. So the PIC-CSCDS was developed that designers could do automobile sketch design on this system. And in this way users and designers could carry out design the automobile sketch cooperatively on image level efficiently

A fuzzy decision model is proposed to select an optimum design from various design alternatives. At the first, the evaluated objectives are arranged in a hierarchical structure with several levels. Secondly the relative contribution of each criterion to the overall value is quantified based on AHP method. Owing to vague concepts of the people' feeling, the information of the degrees of satisfaction of each criteria perceptions of people on the design ideas are quantified with the membership functions of a fuzzy set. Afterward, a weighted generalized mean method is used to calculate the fuzzy probability level by level from the lowest-level objectives. After the fuzzy expected values of the top-level objectives are calculated, they are then used to make a decision quantitatively on selecting the optimal design alternative. Although a cash register is taken as an example in this study, this method can also be used on other products.

One of the problems in building collaborative and intelligent design systems is the difficulty in integrating computer supported collaborative work (CSCW) with knowledge to generate results to the satisfaction of designers who often have high demands on aesthetics. In order to assist designers in the early stages of a product development this paper develops an intelligent methodology for integrating user knowledge and design knowledge. Taken the mobile phone form design as an example, a prototype intelligent conceptual design system is implemented, which consists essentially of the knowledge agents, each of which is a knowledge system with the capabilities of problem reasoning and learning. With this system, product designer and user can carry out simultaneously and intelligently in an Internet-based computer-aided product concurrent design system.

This paper describes a theory called conditional Dempster-Shafer (CDS). This theory provides a unified frame to solve the knowledge updating problem about an uncertain variable. We assume that a priori knowledge about an uncertain variable is modelled by a fuzzy measure and the evidences under the underlying uncertain variable are modelled by the Dempster-Shafer belief measures. The updated knowledge about the uncertain variable is still represented by a fuzzy measure. The updating process of knowledge is as follows: the evidences about the uncertain variable are firstly fused by the rule of conditioned Dempster-Shafer combination proposed in this paper, then the updated knowledge about the variable is achieved using the conditioned agreement function on the combined evidence. We show that the updated knowledge can be represented as a conditional fuzzy measure given the evidences.

The objective of computer supported knowledge aided collaborative conceptual design (CSKACCD) is to aid group design activities semi-automatically or automatically with multidisciplinary knowledge. This paper presents a general distributed design system model to give a global view of CSKACCD, and then designs a constraint-based distributed knowledge representation model based on different constraints abstracted from the domain specific knowledge of the designing artifact. Finally, this paper describes a robust distributed conflict detection and resolution mechanism developed for different designers to interact with each other effectively.