scispace - formally typeset
Search or ask a question

Showing papers on "Interactive video published in 2018"


Journal ArticleDOI
TL;DR: The design guidelines derived in this study can serve as reference for instructors to create interactive video lectures with CI-based ILAs in digital learning contexts and do not impose any additional cognitive load on learners.
Abstract: The increased interaction with multimedia content has been recognized as a significant factor to improve learners’ learning outcomes. As a result, interactive video lectures are increasingly being adopted in digital learning contexts for increasing interactivity. However, conventional video lecture lacks interactive learning activities (ILAs) that are an indispensable component of interactivity. Interactive video lectures can provide learners opportunities to obtain timely constructive support to produce effective learning outcomes because of ILAs. In order to carefully design and create ILAs for effective learning, instructors need to invest substantial efforts for conceiving the content and interactions of ILAs. This study proposed an approach to design the content of ILAs by leveraging collective intelligence (CI) gathered from the discussion forums specifically related to the content of video lectures. When learners exercised ILAs, meaningful interactions by speaking and gesturing worked as learning support to improve comprehension of learning materials. To evaluate the effects of the CI-based ILAs, an experiment was conducted with 90 university students, who were randomly and equally assigned to three different groups (i.e., embodied interactive, non-embodied interactive, and conventional video lectures). The results show that learners who learned with the embodied interactive video lecture performed better in comprehension and retention of learning contents than the other two counter groups. The findings also revealed that this approach does not impose any additional cognitive load on learners. The design guidelines derived in this study can serve as reference for instructors to create interactive video lectures with CI-based ILAs in digital learning contexts.

74 citations


Posted Content
TL;DR: This paper proposes a deep interactive image segmentation method, that can accurately segment objects with only a handful of clicks, and can effectively correct frames where the video object segmentation fails, thus allowing users to quickly obtain high quality results even on challenging sequences.
Abstract: In this paper we present our system for human-in-the-loop video object segmentation. The backbone of our system is a method for one-shot video object segmentation. While fast, this method requires an accurate pixel-level segmentation of one (or several) frames as input. As manually annotating such a segmentation is impractical, we propose a deep interactive image segmentation method, that can accurately segment objects with only a handful of clicks. On the GrabCut dataset, our method obtains 90% IOU with just 3.8 clicks on average, setting the new state of the art. Furthermore, as our method iteratively refines an initial segmentation, it can effectively correct frames where the video object segmentation fails, thus allowing users to quickly obtain high quality results even on challenging sequences. Finally, we investigate usage patterns and give insights in how many steps users take to annotate frames, what kind of corrections they provide, etc., thus giving important insights for further improving interactive video segmentation.

49 citations


Journal ArticleDOI
TL;DR: A prototype system containing immersive, interactive 360-degrees videos that can provide the students with novel interaction mechanisms, to improve their skills, and it can be used as a complementary tool for the teaching and learning methods currently used in their education process.
Abstract: Extremely catastrophic situations are rare in Sweden, which makes training opportunities important to ensure competence among emergency personnel who should be actively involved during such situations. There is a requirement to conceptualize, design, and implement an interactive learning environment that allows the education, training and assessment of these catastrophic situations more often, and in different environments, conditions and places. Therefore, to address these challenges, a prototype system has been designed and developed, containing immersive, interactive 360-degrees videos that are available via a web browser. The content of these videos includes situations such as simulated learning scenes of a trauma team working at the hospital emergency department. Various forms of interactive mechanisms are integrated within the videos, to which learners should respond and act upon. The prototype was tested during the fall term of 2017 with 17 students (working in groups), from a specialist nursing program, and four experts. The video recordings of these study sessions were analyzed and the outcomes are presented in this paper. Different group interaction patterns with the proposed tool were identified. Furthermore, new requirements for refining the 360-degrees interactive video, and the technical challenges associated with the production of this content, have been found during the study. The results of our evaluation indicate that the system can provide the students with novel interaction mechanisms, to improve their skills, and it can be used as a complementary tool for the teaching and learning methods currently used in their education process.

27 citations


Journal ArticleDOI
TL;DR: This quasi-experimental study evaluated the impact of interactive video communication versus text-based feedback and found a significant difference between the 2 groups related to teaching, social, and cognitive presence.
Abstract: A key element to online learning is the ability to create a sense of presence to improve learning outcomes. This quasi-experimental study evaluated the impact of interactive video communication versus text-based feedback and found a significant difference between the 2 groups related to teaching, social, and cognitive presence. Recommendations to enhance presence should focus on providing timely feedback, interactive learning experiences, and opportunities for students to establish relationships with peers and faculty.

27 citations


Journal ArticleDOI
27 Oct 2018
TL;DR: This research is an R & D research that is an interactive tutorial video CD-based learning model in visual programming language courses that are more seen, with and practiced and concludes that this instructional media of video tutorials on programming language of visual delphi is feasible to be used and developed.
Abstract: This research is an R & D (research and development) research that is an interactive tutorial video CD-based learning model in visual programming language courses that are more seen, with and practiced. That is, is the development of a model of teaching materials in other forms, which are complementary to existing teaching materials. This application presents material interactively with animation, audio, video and is equipped with an evaluation in the form of practice questions using the Camtasia Studio and Macromedia Flash applications. The results that will be achieved from the making of this learning media is that students can understand the subjects of visual programming language and find out the quality of the interactive video CD tutorial based on the assessment of media experts, material experts and learning. The results of a feasibility assessment of video tutorials learning media for visual programming language subjects are: (1) the percentage score of material expert assessment was 81.25%; (2) the percentage score of media expert assessment was 84.5%; (3) the percentage score of student response was 84.83%. Based on the results of the assessment and responses obtained, we can conclude that this instructional media of video tutorials on programming language of visual delphi is feasible to be used and developed.

24 citations


Journal ArticleDOI
TL;DR: Interactive video games such as “That Dragon, Cancer” may be useful as part of innovative curricula to improve empathy among third-year medical students.
Abstract: Empathy plays an important role for physicians, but the literature demonstrates that it often deteriorates during medical school. The purpose of this study is to investigate the use of the interactive video game “That Dragon, Cancer” as a tool to teach empathy to third-year medical students. The authors gave a modified, Jefferson Scales of Physician Empathy (JSPE) to 84 third-year medical students in their psychiatry clerkship before and after they played and completed “That Dragon, Cancer” during the 2016–2017 academic calendar year. The average level of empathy in the students as measured by least squares means of the answers to the truncated JSPE improved after playing through “That Dragon, Cancer” (5.7738 vs 6.2322, p < 0.0001). The majority of students agreed that learning empathy through video games was preferable and more effective than traditional didactics. Interactive video games such as “That Dragon, Cancer” may be useful as part of innovative curricula to improve empathy among third-year medical students.

22 citations


Journal ArticleDOI
TL;DR: A network-exposed application programming interface (API) that provides visibility into the state of the network, an SDN-assisted congestion control algorithm that utilizes network state information to achieve the desired low latency and high bandwidth utilization requirements, and a fair resource assignment algorithm that shares available bandwidth among interactive and non-interactive traffic dynamically – all without a reservation protocol.

21 citations


Journal ArticleDOI
TL;DR: Fundamental questions are raised regarding the place of the IWB in promoting interaction in the class and on the necessity to promote the teacher’s pedagogic concept in order to increase class interaction.
Abstract: The findings of the research literature about the necessity and contribution of Interactive Whiteboards (IWB) are not unequivocal and are sometimes contradictory. The study aimed to examine the int...

17 citations


Journal ArticleDOI
TL;DR: Examination of the effectiveness of a software that supports formative assessment in real-time of learners' vocabulary knowledge through an interactive highlighting method finds that high school students who learned with interactive highlighting across a 10-week program scored higher on a standardized reading comprehension test as compared to a control group that studied without interactive highlighting.
Abstract: This article examines the effectiveness of a software that supports formative assessment in real-time of learners' vocabulary knowledge through an interactive highlighting method. Students in a classroom are given a passage on their computer screen and asked to highlight the words they do not understand. This information is summarized on the instructors screen by highlighting in red the words most highlighted, in orange the second most highlighted, and in yellow the third most highlighted, with a superscript showing the number of students who selected each word. The instructor projects this summary on a screen for the whole class and use it to guide activities on how to comprehend the passage. In Experiment 1, college students who learned with interactive highlighting in a single-session study scored higher on a vocabulary test (d = 1.14) but not on a comprehension test as compared to a control group that studied the same passage without interactive highlighting. In Experiment 2, high school stude...

17 citations


Patent
06 Nov 2018
TL;DR: In this paper, the authors reveal a video interaction method and device, and a readable medium relating to the field of multimedia, which comprises the steps of playing an interactive video in a video play interface, wherein the interactive video comprises a target story node; when the interactive videos reaches the target story nodes, displaying an interaction control on a target video image of the Interactive video; receiving a trigger operation on the interaction control; and displaying interaction content corresponding to interaction control according to the trigger operation.
Abstract: The invention discloses a video interaction method and device, and a readable medium, relating to the field of multimedia The method comprises the steps of playing an interactive video in a video play interface, wherein the interactive video comprises a target story node; when the interactive video reaches the target story node, displaying an interaction control on a target video image of the interactive video; receiving a trigger operation on the interaction control; and displaying interaction content corresponding to the interaction control according to the trigger operation In the method,the interaction control is added in the target story node in the interactive video, when the user triggers the interaction control, interaction content corresponding to the interaction control is displayed, the user can watch or like a single video, and further can interact with the short video by using the interaction control in the short video, so that the video is more interest, and the problem of single video interaction manner is solved

16 citations


Journal ArticleDOI
TL;DR: The results show that the interactive video is effective to prepare the laboratory work and guide the students’ self‐regulated study, but needs to be complemented with other pedagogical methods to enhance the learning outcomes.
Abstract: This article focus on the pedagogical tools in LABVIRTUAL (http://labvirtual.eq.uc.pt), a broad scope virtual platform intended to support the learning at the undergraduate level of Chemical Engineering courses, mainly in Portuguese‐speaking countries. The platform contains fundamentals, case studies, simulators, virtual laboratories, and, recently, interactive videos for the teaching of chemical processes. The significance and impact of LABVIRTUAL are illustrated with an interactive video regarding the characterization of nanoparticles by dynamic light scattering, developed for long‐distance learning and used in the discipline of Technology of Disperse Systems. Furthermore, two questionnaires were prepared to assess the students’ response to the interactive video and the use of LABVIRTUAL in general. The results show that the interactive video is effective to prepare the laboratory work and guide the students’ self‐regulated study, but needs to be complemented with other pedagogical methods to enhance the learning outcomes. LABVIRTUAL is generally viewed as a valuable learning tool by the students of Separation Processes and Project Design, 3rd and 5th year courses, respectively, of the Masters’ degree in Chemical Engineering of the University of Coimbra, due to the synergy of pedagogical tools that complement well the face‐to‐face classroom lectures. This fact also justifies the high number of monthly visits, including from companies that use the platform as a life‐long learning tool.

Journal ArticleDOI
TL;DR: The use of interactive video simulations was found to be feasible to incorporate into the curriculum and was appealing to students, and students in the simulation arm displayed more behaviors consistent with the patient-centered interviewing model practiced in the simulations.
Abstract: Introduction Effective strategies for teaching communication skills to health professions students are needed. This article describes the design and evaluation of immersive and interactive video simulations for medical students to practice basic communication skills. Methods Three simulations were developed, focusing on patient-centered interviewing techniques such as using open-ended questions, reflections, and empathic responses while assessing a patient's history of present illness. First-year medical students were randomized to simulation or education-as-usual arms. Students in the simulation arm were given access to three interactive video simulations developed using Articulate Storyline, an e-learning authoring tool, to practice and receive feedback on patient-centered interviewing techniques to prepare for their Observed Structured Clinical Examination (OSCE). Trained raters evaluated videos of two OSCE cases for each participant to assess specific communication skills used during the history of present illness component of the interview. Results Eighty-seven percent of the students in the simulation arm interacted with at least one simulation during the history of present illness. For both OSCE cases, students in the simulation arm asked significantly more open-ended questions. Students in the simulation arm asked significantly fewer closed-ended questions and offered significantly more empathic responses in one OSCE case. No differences were found for reflections. Students reported that the simulations helped improve their communication skills. Conclusion The use of interactive video simulations was found to be feasible to incorporate into the curriculum and was appealing to students. In addition, students in the simulation arm displayed more behaviors consistent with the patient-centered interviewing model practiced in the simulations. Continued development and research are warranted.

Journal ArticleDOI
12 Sep 2018
TL;DR: Empirical results indicated that the refined EGameFlow scale, a self-report scale instrument created from the original game enjoyment framework proposed by Sweetser and Wyeth, was both valid and reliable.
Abstract: The development of a relevant model for measuring user enjoyment of video game play has received a great deal of attention in game-based and flow-based literature. EGameFlow, a self-report scale instrument created from the original game enjoyment framework proposed by Sweetser and Wyeth, provides a necessary and potentially useful tool for game enjoyment researchers. However, the scale itself is quite new. The utility of EGameFlow cannot be determined until its rigorousness has been verified. The purpose of this study was to test the validity, reliability, and applicability of EGameFlow for measuring players’ experiences in video game play. A total of 167 participants played an interactive video game and then evaluated their game playing experiences via the refined 27-item EGameFlow scale, which included the following seven dimensions: concentration, goal clarity, feedback, challenge, autonomy, immersion, and social interaction. Confirmatory factor analysis, reliability testing, and discriminant validity checks were administered. Empirical results indicated that the refined scale was both valid and reliable. Implications of these findings and direction for future research were also discussed.

Proceedings ArticleDOI
Jonathan Hook1
25 Jun 2018
TL;DR: An analysis of 43 interactive videos that use data in a noteworthy fashion reveals a design space comprising key techniques for telling engaging interactive video stories with and about data.
Abstract: We live in a society that is increasingly data rich, with an unprecedented amount of information being captured, stored and analysed about our lives and the people we share them with. We explore the relationship between this new data and emergent forms of interactive video storytelling. In particular we ask: i) how can interactive video storytelling techniques be employed to provide accessible, informative and pleasurable ways for people to engage with data; and ii) how can data be used by the creators of interactive video stories to meet expressive goals and support new forms of experience? We present an analysis of 43 interactive videos that use data in a noteworthy fashion. This analysis reveals a design space comprising key techniques for telling engaging interactive video stories with and about data. To conclude, we discuss challenges relating to the production and consumption of such content and make recommendations for future research.

Book ChapterDOI
05 Feb 2018
TL;DR: A custom approach for tackling the problem of finding similarities in the TRECVID IACC.3 dataset via hand-drawn pictures using color compositions together with contour matching, which has first been utilized in the VBS 2017 challenge.
Abstract: Past editions of the annual Video Browser Showdown (VBS) event have brought forward many tools targeting a diverse amount of techniques for interactive video search, among which sketch-based search showed promising results. Aiming at exploring this direction further, we present a custom approach for tackling the problem of finding similarities in the TRECVID IACC.3 dataset via hand-drawn pictures using color compositions together with contour matching. The proposed methodology is integrated into the established Collaborative Feature Maps (CFM) system, which has first been utilized in the VBS 2017 challenge.

Journal Article
TL;DR: This study examined the video-viewing behaviors of students and their reasons for deciding to watch or not watch videos in a hybrid sophomore-level Mechanics of Materials course to show that when students played the videos, they watched most of the content.
Abstract: The hybrid course format has gained popularity in the engineering education community over the past few years. Although studies have examined student outcomes and attitudes toward hybrid courses, a limited number of studies have examined how students interact with online videos in hybrid courses. This study examined the video-viewing behaviors of students and their reasons for deciding to watch or not watch videos in a hybrid sophomore-level Mechanics of Materials course. The findings show that when students played the videos, they watched most of the content; for videos 1 to 22 minutes long, the number of times played and the percentage of videos completed did not vary; the number of times played depended on the difficulty of a video’s topic; and the number of times played increased during exam periods. Students’ reasons for watching or not watching videos were identified. The findings have implications for the development of online videos for hybrid courses and improving engineering student utilization of videos.

Book ChapterDOI
20 Jun 2018
TL;DR: This study provides a review of the interactivity types and their educational value based on the analysis of 18 studies and 13 commercial interactive video environments and provides specific design guidelines for developing effective educational interactive videos.
Abstract: In recent years, there has been a sharp increase of research in employing interactive video for learning. More researchers study both the functional and cognitive interactivity affordances of educational interactive video and try to identify the learning effectiveness of the various supported interactions. In this study, we aim at providing a review of the interactivity types and their educational value based on the analysis of 18 studies and 13 commercial interactive video environments. We also analyze whether the commercial environments keep up with the research trends. Finally, we provide specific design guidelines for developing effective educational interactive videos. Such holistic review approaches help to promote the research field in everyday educational environments but also reveal its promises and gaps. The educational interactive video seems to be a fast-changing field which needs further inquiry, while the available commercial platforms have just started to incorporate functionality proposed in the literature.

01 Jan 2018
TL;DR: What the authors conceptualise as effective learning moments and conditions and how these can be created and maximised through the effective production and manipulation of relevant, purposeful interactive videos are discussed.
Abstract: This paper focuses on the findings of Phases I and II of an institution-wide project on the effective use of interactive video for teaching and learning in a university in New Zealand. Responding to the emerging growth of video in teaching and learning practice and scholarship, and also to the university’s strategic focus on providing blended, flexible learning opportunities, this project explores the ways in which lecturers currently use videos in teaching, their challenges, and their attitudes towards making video as well as students’ perceptions of learning through video. This paper discusses what we conceptualise as effective learning moments and conditions and how these can be created and maximised through the effective production and manipulation of relevant, purposeful interactive videos. The overall project combines both research and impact and develops opportunities for lecturers to enhance their competencies in creating interactive videos.

Journal ArticleDOI
TL;DR: Results indicated that the HV lessons supported learning more effectively than traditional lessons, providing an encouraging starting point for scholars who would like to investigate the functional integration of HV in educational practices.
Abstract: Recent technological advances are rekindling educational interest in hypervideo (HV). HV provides a good opportunity for enhanced teaching and learning thanks to its affordances for interactivity (...

Proceedings ArticleDOI
07 Aug 2018
TL;DR: Factors for assessing moral engagement in games are proposed, that build upon the general aggression model, the moral disengagement model, and the self-determination theory.
Abstract: The present paper focuses on moral choices in interactive narrative games Particularly, it investigates factors that contribute to moral engagement in short-term decision making in games; as opposed to the somewhat better understood factors that underlie moral disengagement in games To this end, the paper proposes factors for assessing moral engagement in games, that build upon (1) the general aggression model, (2) the moral disengagement model, and (3) self-determination theory The paper reports on two case studies that explore the factors in actual interactive video games; it investigates meaningful choices in the games Life is Strange and The Walking Dead Season 1

Proceedings ArticleDOI
15 Oct 2018
TL;DR: This tutorial discusses interactive video search tools and methods, review their need in the age of deep learning, and explores video and multimedia search challenges and their role as evaluation benchmarks in the field of multimedia information retrieval.
Abstract: In this tutorial we discuss interactive video search tools and methods, review their need in the age of deep learning, and explore video and multimedia search challenges and their role as evaluation benchmarks in the field of multimedia information retrieval. We cover three different campaigns (TRECVID, Video Browser Showdown, and the Lifelog Search Challenge), discuss their goals and rules, and present their achieved findings over the last half-decade. Moreover, we talk about datasets, tasks, evaluation procedures, and examples of interactive video search tools, as well as how they evolved over the years. Participants of this tutorial will be able to gain collective insights from all three challenges and use them for focusing their research efforts on outstanding problems that still remain unsolved in this area.

Patent
20 Apr 2018
TL;DR: In this article, a story branch video playing method and device is described, through which the viewing cost of a user can be reduced, and the viewing experience of the user can also be improved.
Abstract: The invention relates to the technical field of videos, and discloses a story branch video playing method and device, through which the viewing cost of a user can be reduced, and the viewing experience of the user can be improved. The method comprises the following steps: when playing reaches a story branch unfolding node in an interactive video, acquiring story branch prompt information to be unfolded for display on the node, and playing authority information of story branch videos corresponding to the story branch prompt information; displaying the playing authority information required forthe playing of the corresponding story branch videos while unfolding the story branch prompt information for display; when a story branch selection command is received, determining a story branch video to be played which is selected by the user; and according to the playing authority information corresponding to the story branch video to be played and video subscription information corresponding to the user, determining whether to play the story branch video to be played or not. The method and device provided by the invention is applicable for the story branch video playing.

Patent
05 Jun 2018
TL;DR: In this article, an interactive video generation method and device, which relates to the technical field of videos, is presented. But the authors mainly aim to solve the problems that generation of a multi-storyline interactive video cannot be realized and various branch plots corresponding to the interactive video can be intuitively displayed in the existing current interactive video manufacturing manner.
Abstract: The invention discloses an interactive video generation method and device, relates to the technical field of videos, and mainly aims to solve the problems that generation of a multi-storyline interactive video cannot be realized and various branch plots corresponding to the interactive video cannot be intuitively displayed in the existing current interactive video manufacturing manner. A main technical scheme comprises the steps of: receiving a plot selection instruction input by a user, wherein the plot selection instruction carries plot information; extracting materials matched with the plotinformation, wherein the materials include plot information generated by storylines having different plots; receiving a material selection instruction input by the user, wherein the material selection instruction carries a target material selected from the matched materials by the user, and a target position selected from the plot information by the user; and, configuring the target material in the target position, and generating an interactive video according to the configured plot information.

Proceedings Article
01 Jan 2018
TL;DR: Training opportunities are important to secure the competence among emergency personnel that should be actively involved during those situ ...
Abstract: Extreme catastrophe situations are rare in Sweden, which makes training opportunities important to secure the competence among emergency personnel that should be actively involved during those situ ...

Patent
26 Apr 2018
TL;DR: In this paper, a method for intelligently connecting seekers to advisors and providing recorded or synthesized answers to the seekers using artificial intelligence is provided, where the call is rescheduled for alternate time windows of the advisor or with an alternate advisor and recording and storing the call for automating the answers to similar questions.
Abstract: A method for intelligently connecting seekers to advisors and providing recorded or synthesized answers to the seekers using artificial intelligence is provided. Receiving a topic of interest from a seeker or retrieving advisors with expertise in the topic from a database of advisors, filtering and sorting the advisors based on ratings associated with each of the advisors related to the topic using machine learning and a plurality of criteria specified by the seeker, routing and establishing a call between the seeker and advisor, when the advisor is unavailable the call is rescheduled for alternate time windows of the advisor or with an alternate advisor and recording and storing the call for automating the answers to the similar questions, obtaining feedback from the seeker for the advisor, and updating the intelligent call routing system and the rankings of the advisor based on the plurality of criteria.

Patent
12 Jun 2018
TL;DR: In this article, an interaction method and device of interactive video playing was proposed to solve the problem that the existing video show cannot meet demands of different users for selecting branch scenarios as the video show is a scenario of a single story line.
Abstract: The invention discloses an interaction method and device of interactive video playing, and relates to the technical field of videos. The interaction method and device of interactive video playing mainly aims at solving the problem that the existing video show cannot meet demands of different users for selecting branch scenarios as the existing video show is a scenario of a single story line and audiences when watching the existing video receive the scenario of the single story line passively. The main technical scheme comprises the steps of receiving a triggering mode input by a user in an interactive video playing process, wherein the interactive videos are videos of different scenarios generated based on development of different story lines; parsing a triggering event corresponding to the triggering mode and identifying the playing state of the current interactive video; and performing an interactive operation which matches the triggering event and the playing state.

Journal Article
TL;DR: The practical aspects of producing 360-degree-video content that can be shared online or in a classroom setting are addressed.
Abstract: A 360-degree video is a powerful tool that can bring learners into environments that would otherwise be inaccessible. These videos are simultaneously recorded in all directions, allowing the viewer to control viewing direction. Viewers can experience these videos on a computer, smartphone, or tablet or with a virtual reality headset. Camera and software equipment needed to produce 360-degree videos is affordable, allowing Extension educators to produce their own videos. This article addresses the practical aspects of producing 360-degree-video content that can be shared online or in a classroom setting.

Proceedings ArticleDOI
01 Oct 2018
TL;DR: A new approach for semantic browsing in a large video collection is proposed based, essentially, on a structuring of the video concepts based on a weight calculated to measure the membership degree of a concept at different levels (context / concept / video).
Abstract: Following the technological advances carried out recently, there was an explosion in the number of available videos and their accessibility. This was largely justified by the fall of the acquisition prices of the memory supports and the increase their capacity, which facilitated the storage of a large number of video document databases in the computer systems. To make the exploitation of these collections effective, it is necessary to install tools that facilitate access and handle them. In this paper, we propose a new approach for semantic browsing in a large video collection. Our approach is based, essentially, on a structuring of the video concepts. Indeed, a weight is calculated to measure the membership degree of a concept at different levels (context / concept / video). We developed the Video Navigation System (VINAS) to test our approach. A visual metaphor inspired by tag cloud concept is also set up in our VINAS system to help with the comprehensive semantic video browsing. A user study made on our VINAS system showed that the proposed approach can help the user with the semantic browsing in video collection.

Posted Content
TL;DR: This work proposes neural network based attention modules, capable of weighting different portions (spatio-temporal blocks) of the video based on their respective discriminative power, and indicates that incorporating attention modules yields state-of-the-art results for the audio-visual synchronization classification problem.
Abstract: With the development of media and networking technologies, multimedia applications ranging from feature presentation in a cinema setting to video on demand to interactive video conferencing are in great demand. Good synchronization between audio and video modalities is a key factor towards defining the quality of a multimedia presentation. The audio and visual signals of a multimedia presentation are commonly managed by independent workflows - they are often separately authored, processed, stored and even delivered to the playback system. This opens up the possibility of temporal misalignment between the two modalities - such a tendency is often more pronounced in the case of produced content (such as movies). To judge whether audio and video signals of a multimedia presentation are synchronized, we as humans often pay close attention to discriminative spatio-temporal blocks of the video (e.g. synchronizing the lip movement with the utterance of words, or the sound of a bouncing ball at the moment it hits the ground). At the same time, we ignore large portions of the video in which no discriminative sounds exist (e.g. background music playing in a movie). Inspired by this observation, we study leveraging attention modules for automatically detecting audio-visual synchronization. We propose neural network based attention modules, capable of weighting different portions (spatio-temporal blocks) of the video based on their respective discriminative power. Our experiments indicate that incorporating attention modules yields state-of-the-art results for the audio-visual synchronization classification problem.

Journal ArticleDOI
TL;DR: In this paper, the authors describe how one of these tools is used in international communication with different digital tools, both atuniversities and in other contexts worldwide, and describe how these tools are used in different contexts.
Abstract: International communication with different digital tools is now established both atuniversities and in other contexts worldwide. It is therefore relevant to describe howone of these tools is used i ...