Field Of Multimedia Research Articles

Designing of Android Based Learning (Mobile Learning) for Multidiscipline Students

A breakthrough in the multimedia field is needed by creating varied learning strategies to attract students’ interest in learning. The purpose of this study is to create learning media M-Learning to support the learning process in Vocational High School and to know the level of prevalence M-Learning as a medium of learning. The research method using Research and Development which has eight stages: 1) Identification of Research Needs, 2) Purpose Formulation, 3) Formulation of material items, 4) Formulation of success tools, 5) Media manuscript formulation, 6) Tests or product trials, 7) Revisions, 8) Manuscripts are ready to be produced. This media is developed using Android Studio. The result of this research is a dynamic Android-based application that is run online as a supporter of learning. The results of validator assessment and student response can be obtained from the media expert value at 65% in the sense of valid, acquiring a low score due to a lot of revision of the application. According to the material experts, the media obtains the value of 85% which means valid, and a validity score of 94.7% is obtained from students’ responses that mean valid. The conclusion shows that validator assessments of learning media can be used as supporting self-study, especially for multidiscipline students.

A Semi-Fragile Video Watermarking Algorithm Based on H.264/AVC

With the increasing application of advanced video coding (H.264/AVC) in the multimedia field, a great significance to research in video watermarking based on this video compression standard has been established. We propose a semifragile video watermarking algorithm, which can simultaneously implement frame attack and video tamper detection, herein. In this paper, the frame number is selected as the watermark information, and the relationship of the discrete cosine transform (DCT) nonzero coefficients is used as the authentication code. The 4×4 subblocks, whose DCT nonzero coefficients are sufficiently complex, are selected to embed the watermark. The parities of these nonzero coefficients in the medium frequency are modulated to embed watermarks. The experimental results show that the visual quality of the embedded watermarked video is virtually unaffected, and the algorithm exhibits good robustness. Furthermore, the algorithm can correctly implement frame attack and video tamper detection.

Image to Modern Chinese Poetry Creation via a Constrained Topic-aware Model

Artificial creativity has attracted increasing research attention in the field of multimedia and artificial intelligence. Despite the promising work on poetry/painting/music generation, creating modern Chinese poetry from images, which can significantly enrich the functionality of photo-sharing platforms, has rarely been explored. Moreover, existing generation models cannot tackle three challenges in this task: (1) Maintaining semantic consistency between images and poems; (2) preventing topic drift in the generation; (3) avoidance of certain words appearing frequently. These three points are even common challenges in other sequence generation tasks. In this article, we propose a Constrained Topic-aware Model (CTAM) to create modern Chinese poetries from images regarding the challenges above. Without image-poetry paired dataset, we construct a visual semantic vector to embed visual contents via image captions. For the topic-drift problem, we propose a topic-aware poetry generation model. Additionally, we design an Anti-frequency Decoding (AFD) scheme to constrain high-frequency characters in the generation. Experimental results show that our model achieves promising performance and is effective in poetry’s readability and semantic consistency.

Listen, Look, and Find the One

Person search with one portrait, which attempts to search the targets in arbitrary scenes using one portrait image at a time, is an essential yet unexplored problem in the multimedia field. Existing approaches, which predominantly depend on the visual information of persons, cannot solve problems when there are variations in the person’s appearance caused by complex environments and changes in pose, makeup, and clothing. In contrast to existing methods, in this article, we propose an associative multimodality index for person search with face, body, and voice information. In the offline stage, an associative network is proposed to learn the relationships among face, body, and voice information. It can adaptively estimate the weights of each embedding to construct an appropriate representation. The multimodality index can be built by using these representations, which exploit the face and voice as long-term keys and the body appearance as a short-term connection. In the online stage, through the multimodality association in the index, we can retrieve all targets depending only on the facial features of the query portrait. Furthermore, to evaluate our multimodality search framework and facilitate related research, we construct the Cast Search in Movies with Voice (CSM-V) dataset, a large-scale benchmark that contains 127K annotated voices corresponding to tracklets from 192 movies. According to extensive experiments on the CSM-V dataset, the proposed multimodality person search framework outperforms the state-of-the-art methods.

People’s Reflections in the City: Exploring the Painting Practices of Figurative Expressionism by Academic Research

This paper is a practical outcome of a multidisciplinary research project conducted by the authors on the contemporary and modern practices of the Improvisation in Arts. All the authors are research-oriented practitioners in the fields of visual arts, performance arts, multimedia, Information and communication technologies as well as vocational training. Furthermore, the drawings, paintings, and sketches are all made by the correspondent author Assistant Professor Dr. Mohammed Baker Mohammed Al-Abbas as part of his research-oriented artistic practice through the hybrid painting techniques. Abstract The present studio-based paper aims to explore the creative reflections of the aesthetics of otherness within the practical phases of the painting production. This paper represents an experimental endeavor to create a two-dimensional artwork, which is a hybrid painting technique on canvas with mixed media and acrylic paints. Within such a specific practice-based context, each phase of this practical approach outlines a critical significance from the first phase of creating that painting to the completing phase. The practical methodology is the tool that converts the researcher's/artist's vision into creative academic production. The process of creating the painting on the canvas is the methodology; such manner turns to be a primary reference for the present exploration. There is a significant paradigm in this approach, which focuses on the artwork as a morphological creature being created by the researcher/artist rather than a consequent result that only exists as a finished/complete/polished outcome. The outcome of this research is the record of the artwork production itself. This record presents visual references of the artwork progress as well as a textual reflective narrative to describe this process with written words. This research-oriented artistic attempt introduces the artists and researchers in the domains of the Fine Arts to integrate the process of art-making into the methodologies of academic research. It is an academic text, reflective text as well as sequential images recording the artwork making. This studio-based experimentation is significant because it examines the aesthetics of the otherness into the expressive figurative abstraction in painting. Furthermore, the impact of such a studio-based approach manifests on advancing applications of the artistic oriented research in the field of Fine Arts globally on curatorial and academic levels. Keywords: Contemporary Art Practice, Studio-Based Methodology, Practice-Based Research, Hybrid Painting Techniques, Multimedia, Mixed media, Photography DOI: 10.7176/JEP/11-10-08 Publication date: April 30 th 2020

Wavelet Techniques for Medical Images Performance Analysis and Observations with EZW and Underwater Image Processing

The digitized image has an important role in the compression. Compression encodes the image using a certain algorithm with less number of bits and decompression decoded this image in original form using a different algorithm. The clinical environment and hospitals are moving towards digitization, computerization and centralization in the field of medical image processing. Content based compressions (CBC) techniques turns more considerable in the field of medical image processing and multimedia. However, CBC techniques alone are not adequate for all medical image processing applications. Therefore, in this paper, the EZW algorithm has been discussed with Haar wavelet and Bior4.4 technique on skeleton images with different type of image quality parameters. The analysis shows that the compression ratio (CR) of EZW with Bior4.4 on skeleton image is 44.19%, MSE is 527.73 and PSNR is 45.45. While, the CR of EZW with Haar on the same image is 40.31%, MSE is 699 and PSNR is 35.34 db. Further EZW can help precise capacity of amount, exterior area and other morph metric capacity of organic stuff, lacking removing them commencing the sea or in the marine environment.

Multi-Person Pose Estimation Using an Orientation and Occlusion Aware Deep Learning Network.

Image based human behavior and activity understanding has been a hot topic in the field of computer vision and multimedia. As an important part, skeleton estimation, which is also called pose estimation, has attracted lots of interests. For pose estimation, most of the deep learning approaches mainly focus on the joint feature. However, the joint feature is not sufficient, especially when the image includes multi-person and the pose is occluded or not fully visible. This paper proposes a novel multi-task framework for the multi-person pose estimation. The proposed framework is developed based on Mask Region-based Convolutional Neural Networks (R-CNN) and extended to integrate the joint feature, body boundary, body orientation and occlusion condition together. In order to further improve the performance of the multi-person pose estimation, this paper proposes to organize the different information in serial multi-task models instead of the widely used parallel multi-task network. The proposed models are trained on the public dataset Common Objects in Context (COCO), which is further augmented by ground truths of body orientation and mutual-occlusion mask. Experiments demonstrate the performance of the proposed method for multi-person pose estimation and body orientation estimation. The proposed method can detect 84.6% of the Percentage of Correct Keypoints (PCK) and has an 83.7% Correct Detection Rate (CDR). Comparisons further illustrate the proposed model can reduce the over-detection compared with other methods.

Image Encryption Algorithm Based on a Novel Six-Dimensional Hyper- Chaotic System

Due to the rapid evaluation in the field of communications and multimedia and the increasing use of the Internet, multimedia data security has become very urgent. of the best alternative way to achieve multimedia data security is encryption, which prevents unauthorized entities from accessing confidential data. In recent years, the chaotic system of image encryption becomes an efficient way to encrypt images due to its high security. It has certain special properties like sensitivity to initial conditions, and control parameters, pseudorandom, ergodicity, and non-convergence, etc. chaotic dynamics systems became a promising alternative to traditional encryption algorithms. In this paper, This paper presents a new algorithm for the image encryption/decryption scheme depended on a novel six-dimensional hyper-chaotic system to achieve a high level of security, the chaotic sequence generated from system employ for permutation and diffusion the original image to create an encrypted image. The performance of the algorithm has been analyzed through analyzes statistical such as Histogram Analysis, Correlation Coefficient Analysis, Information Entropy Analysis, Key Space Analysis, Key Sensitivity Analysis, Number of Pixels Change Rate (NPCR), Unified Average Changing Intensity (UACI), Peak Signal to Noise Ratio, The experimental results show that the algorithm has good encryption performance, large keyspace equals to and the high sensitivity for small changes in secret key which makes the algorithm immune to Brute force attacks, and it can resist the statistical attacks, therefore, the presented encryption algorithm depends on a novel hyperchaotic system is more secure against the statistical and differential attacks.

AUGMENTED REALITY SEBAGAI MEDIA PENDIDIKAN KESEHATAN UNTUK ANAK USIA SEKOLAH

Technology in the multimedia field that is currently developing is Augmented Reality (AR). Utilization of Augmented Reality as a medium for children's education provides a new perspective on the existing educational media, not only using real objects but also using virtual objects in the delivery of information. AR is a technology that combines three-dimensional virtual objects into a real three-dimensional environment and displays them in real time. AR can make delivery easier and make information more interesting especially for children. AR is expected to be able to support as one of the media for school-age children in an effort to realize health promotion. This research method uses a literature review that focuses on the use of Augmented Reality as a medium for health education for school-age children. The literature used is in the form of articles originating from national and international journals. The application of AR as an educational medium can increase children's knowledge. In Indonesia the use of AR media has not been implemented much less especially in nursing. The need for the development of this AR media in the world of nursing.

3D shape recognition based on multi-modal information fusion

The classification and retrieval of 3D models have been widely used in the field of multimedia and computer vision. With the rapid development of computer graphics, different algorithms corresponding to different representations of 3D models have achieved the best performance. The advances in deep learning also encourage various deep models for 3D feature representation. For multi-view, point cloud, and PANORAMA-view, different models have shown significant performance on 3D shape classification. However, There’s not a way to consider utilizing the fusion information of multi-modal for 3D shape classification. In our opinion, We propose a novel multi-modal information fusion method for 3D shape classification, which can fully utilize the advantage of different modal to predict the label of class. More specifically, the proposed can effectively fuse more modal information. it is easy to utilize in other similar applications. We have evaluated our framework on the popular dataset ModelNet40 for the classification task on 3D shape. Series experimental results and comparisons with state-of-the-art methods demonstrate the validity of our approach.

Comparison of Use of Music Content (Tempo) and User Context (Mood) Features On Classification of Music Genre

The development of technology in the current era in the field of multimedia, music is not just entertainment or pleasure. Nowadays, online music growth is greatly increasing, namely, music can be classified by genre. The music genre is the grouping of music according to their resemblance to each other. In previous studies, the system was built with Naive Bayes Classifier which is useful for predicting songs based on the lyrics of the song. In our study, we used a dataset that was divided into several genera, namely Blues, Electronic, R & B, Christian, Hip Hop / Rap, Rock, Country, Jazz, Ska, Dance, Pop, and Soul which obtained the accuracy of Music Content of 45 % while for Context Users get an accuracy of 60%.
 Keywords : Genre, Naive Bayes, Music Content, User Context

MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval

3D shape retrieval is an important researching field due to its wide applications in computer vision and multimedia fields. With the development of deep learning technology, great progress has been made in recent years and lots of methods have achieved promising 3D shape retrieval results. Due to the effective description of point cloud data on structural information for 3D shapes, lots of methods based on point cloud data format are proposed for better shape representation. However, most of them focus on extracting a global descrisptor from the whole 3D shape while the local features and detailed structural information are ignored, which negatively affect the effectiveness of shape descriptors. In addition, these methods also ignore the correlations among different parts of point clouds, which may introduce redundant information to the final shape descriptors. In order to address these issues, we propose a Multi-part attention network (MPAN) for 3D model retrieval based on point cloud. Firstly, we segment a 3D shape into multiple parts by employing a pre-trained PointNet++ segmentation model. After extracting the local features from them, we introduce a novel self-attention mechanism to explore the correlations between different parts. Meanwhile, by considering the structural relevance of them, the redundancy for representing 3D shapes is removed while the effective information is utilized. Finally, informative and discriminative shape descriptors, considering both local features and spatial correlations, are generated for 3D shape retrieval task. To validate the effectiveness of our method, we conduct several experiments on the public 3D shape benchmark, ShapeNetPart dataset. Experimental results and comparisons with state-of-the-art methods demonstrate the superiority of our proposed method.

Tumor Detection in MRI Brain Images Based on Saliency Computational Modeling

Abstract In recent years, the issue of tumor detection for Magnetic Resonance Imaging (MRI) brain images has become a research hotspot in the field of medical imaging, multimedia and pattern recognition. In this paper, we propose a tumor detection method based on saliency modeling for MRI brain images. Firstly, in order to overcome the influence of the skull, we utilize the morphological method to strip the skull of the MRI brain images. Then, we introduce a principal local contrast based saliency-detection method to enhance the foreground regions which facilitates to get the leision region. Finally, the results are further improved by denoising, segmentation and morphological operations. Experiments performed on MRI brain images show that the proposed method is useful and effective.

Food Recommendation: Framework, Existing Solutions, and Challenges

A growing proportion of the global population is becoming overweight or obese, leading to various diseases (e.g., diabetes, ischemic heart disease and even cancer) due to unhealthy eating patterns, such as increased intake of food with high energy and high fat. Food recommendation is of paramount importance to alleviate this problem. Unfortunately, modern multimedia research has enhanced the performance and experience of multimedia recommendation in many fields such as movies and POI, yet largely lags in the food domain. This article proposes a unified framework for food recommendation, and identifies main issues affecting food recommendation including building the personal model, analyzing unique food characteristics, incorporating various context and domain knowledge. We then review existing solutions for these issues, and finally elaborate research challenges and future directions in this field. To our knowledge, this is the first survey that targets the study of food recommendation in the multimedia field and offers a collection of research studies and technologies to benefit researchers in this field.

RealPoint3D: Generating 3D Point Clouds from a Single Image of Complex Scenarios

Generating 3D point clouds from a single image has attracted full attention from researchers in the field of multimedia, remote sensing and computer vision. With the recent proliferation of deep learning, various deep models have been proposed for the 3D point cloud generation. However, they require objects to be captured with absolutely clean backgrounds and fixed viewpoints, which highly limits their application in the real environment. To guide 3D point cloud generation, we propose a novel network, RealPoint3D, to integrate prior 3D shape knowledge into the network. Taking additional 3D information, RealPoint3D can handle 3D object generation from a single real image captured from any viewpoint and complex background. Specifically, provided a query image, we retrieve the nearest shape model from a pre-prepared 3D model database. Then, the image, together with the retrieved shape model, is fed into RealPoint3D to generate a fine-grained 3D point cloud. We evaluated the proposed RealPoint3D on the ShapeNet dataset and ObjectNet3D dataset for the 3D point cloud generation. Experimental results and comparisons with state-of-the-art methods demonstrate that our framework achieves superior performance. Furthermore, our proposed framework works well for real images in complex backgrounds (the image has the remaining objects in addition to the reconstructed object, and the reconstructed object may be occluded or truncated) with various viewing angles.

Improved Image Compression Scheme Using Hybrid Encoding Algorithm

A color image compression is the most challenging task in the field of multimedia. During last decades several techniques are developed for improving the quality, coding time and compression ratio using different coding strategies. In this work, an effective compression method for hybrid images is proposed based on the discrete wavelet transformation and hybrid encoding algorithm (Huffman and SPIHT). This paper's primary participation is to take advantage of the hybrid encoding technique to maintain the quality of the reconstructed image and the reduction of time complexity. The sample test images are taken from both standard image database and high-quality images (SD and HD). The performance of the proposed scheme is evaluated by using different metrics such as (PSNR, compression ratio and encoding time). Test results indicate that the time and compression ratio of encoding are improved in the expense of the image quality.

Uni-and-Bi-Directional Video Prediction via Learning Object-Centric Transformation

Video prediction, including uni-directional prediction for future frames and bi-directional prediction for in-between frames, is a challenging task and a problem worth exploring in multimedia and computer vision fields. Existing practices usually make predictions by learning global motion information from the whole given image. However, humans often focus on key objects carrying vital motion information instead of the entire frame. Besides, different objects often show different movement and deformation, even in the same scene. In this connection, we build a novel model of object-centric video prediction, in which the motion signals of key objects are particularly learned. This model can predict new frames by repeatedly transforming objects into the original input images. To focus on these objects automatically, we create an attention module with substitutable strategies. Our method requires no annotated data, and we also use adversarial training to improve sharpness of the predictions. We evaluate our model through Moving MNIST, UCF101 and Penn Action datasets and achieve competitive results in both quantity and quality, compared to existing methods. The experiments demonstrate that our uni-and-bi-directional network can well predict motions for different objects and generate plausible future and in-between frames.

ACTIONS OF INTERNATIONALIZATION OF THE POSTGRADUATE PROGRAMS IN LIBRARIANSHIP, INFORMATION SCIENCE AND DOCUMENTATION: BRAZIL AND PORTUGAL

Study of the implemented actions by the Brazilian and Portuguese coordinators of the Graduate Programs of the areas of Librarianship, Information Sciences and Documentation for the internationalization and visibility of the academic and scientific work. This research is characterized as a study of multiple cases of qualitative-interpretative nature, using content analysis as a research technique. Its relevance lies in the field of Multimedia and Education and Information Science. For this purpose, interviews were conducted with the coordinators of the selected Programs as scenarios of this study, linked to Public Higher Education Institutions (HEIs) located in Brazil and Portugal. The results present the internationalization actions developed by the respondents through agreements, agreements and cooperation established with professors / researchers from foreign universities, aiming at professional qualification, as well as the establishment of partnerships for the development of collaborative writing for publications of works, preferably , in English language in indexed journals, for the development of research projects, participation in international events such as lecturers or for presentation of papers, as well as evaluators of international journals. Considering the results demonstrated by the information gathered through the interviews, it is concluded that these subjects recognize the potential of internationalization as a prerequisite for the expansion of the prestige and recognition of these scientific communities.

Learning Scene Attribute for Scene Recognition

Scene recognition has been a challenging task in the field of computer vision and multimedia for a long time. The current scene recognition works often extract object features and scene features through CNN, and combine these two types of features to obtain complementary and discriminative scene representations. However, when the scene categories are visually similar, the object features might lack of discriminations. Therefore, it may be debatable to consider only object features. In contrast to the existing works, in this paper, we discuss the discrimination of scene attributes in local regions and utilize scene attributes as the complementary features of object and scene features. We extract these visual features from two individual CNN branches, one extracting the global features of the image while the other extracting the features of local regions. Through contextual modeling framework, we aggregate these features and generate more discriminative scene representations, which achieve better performance than the feature aggregation of object and scene. Moreover, we achieve the new state-of-the-art performance on both standard scene recognition benchmarks by aggregating more complementary visual features: MIT67 (88.06%) and SUN397 (74.12%).

Joint Deep and Depth for Object-Level Segmentation and Stereo Tracking in Crowds

Tracking multiple people in crowds is a fundamental and essential task in the multimedia field. It is often hindered by difficulties, such as dynamic occlusion between objects, cluttered background, and abrupt illumination changes. To respond to this need, in this paper, we combine deep and depth to build a stereo tracking system for crowds. The core of the system is the fusion of the advantages of deep learning and depth information, which is exploited to achieve object segmentation and improve the multiobject tracking performance in severe occlusion. More specifically, first, to obtain more accurate detection observations in the tracking system, we present a novel object-level segmentation method. This method combines the effective detection results of deep learning with depth information to obtain precise object segmentation results. Then, we integrate the segmentation results and three-dimensional (3-D) information to extract 2-D and 3-D characteristics to represent the target, and design three similarity models to realize a stereo tracking method through data association in crowds. Finally, we build a diverse stereo dataset including various challenging indoor and outdoor scenes. The comprehensive experiments verify the effective and robust tracking performance of our system in various scenarios, and the system has rich output results including segmentation results, target distance, and tracking results. Moreover, the qualitative and quantitative comparison results show that the proposed algorithm not only has good object segmentation performance but also improves the tracking performance of completely and partially occluded objects, which is superior to the tested state-of-the-art tracking approaches.