This thesis presents several descriptor selection schemes for video content pairwise-matching tasks. Those proposed schemes attempt to leverage two significant properties of videos, temporal correlation and motion information. Aiming to find an efficient and descriptive representation for a video sequence, the concept of descriptor persistency is defined. Those descriptors that satisfy this definition are called persistent descriptors. In order to exploit descriptor persistency, an encoder is proposed. The proposed encoder consists of five main components. First, keyframe labelling is introduced to reduce complexity and ensure a reasonable size of persistent sets. After that, persistent descriptor detection is performed on each group of pictures (GOP) separately. The second component is the standard SIFT descriptor extraction. The third part is to identify persistent descriptors from each GOP, called persistent descriptors extraction. In this stage, three different methods are proposed: The direct method and two approximation approaches. Persistent descriptors selection, which is the fourth stage, is carried out to control the size of the persistent set. For this stage, three selection methods are proposed. All of them attempt to utilize the motion information to select more descriptive descriptors among all the persistent descriptors in the GOP. In order to perform pairwise-matching, in this thesis, a simple but efficient pairwise-matching method is proposed. Experiments are carried out to evaluate the performance of the proposed schemes. The datasets used for performance evaluation are subsets from the categories that describe in [1]. Two metrics de ned in [2], namely false positive rate (FPR) and true positive rate (TPR), are used for the performance evaluation. / Thesis / Master of Applied Science (MASc)

The thesis aims to examine the 'Komentář za minutu' format, published by the online offshoot of 'Hospodářské noviny' daily from November 2014 to January 2017. The theoretical part brings forward the Economia publishing house in context of corporate convergence, as well as attributes of comment genres, online videos, and particularities of audio-visual instruments. The practical part qualitatively analyses data acquired by interviews with journalists of 'Hospodářské noviny' daily who featured in Komentář za minutu. All interviews are included.

Recent increase in the use of video in many applications has revealed the need for extracting the content in videos. Raw data and low-level features alone are not sufficient to fulfill the user&#039 / s need / that is, a deeper understanding of the content at the semantic level is required. Currently, manual techniques are being used to bridge the gap between low-level representative features and high-level semantic content, which are inefficient, subjective and costly in time and have limitations on querying capabilities. Therefore, there is an urgent need for automatic semantic content extraction from videos. As a result of this requirement, we propose an automatic semantic content extraction system for videos in terms of object, event and concept extraction. We introduce a general purpose ontology-based video semantic content model that uses object definitions, spatial relations and temporal relations in event and concept definitions. Various relation types are defined to describe fuzzy spatio-temporal relations between ontology classes. Thus, the video semantic content model is utilized to construct domain ontologies. In addition, domain ontologies are enriched with rule definitions to lower spatial relation computation cost and to be able to define some complex situations more effectively. As a case study, we have performed a number experiments for event and concept extraction in videos for basketball and surveillance domains. We have obtained satisfactory precision and recall rates for object, event and concept extraction. A domain independent application for the proposed framework has been fully implemented and tested.

This work presents an interactive visualization tool for video content searching for lecture videos in a flipped classroom course Visualization. The search is performed using the video caption with a client-site search engine Lunr. The tool aims to improve accessibility to course video materials and enhance learning engagement, especially when students re-watch the videos. The work focus on using interactive visualization method to help users understand the results and seek video chapters of interest. We evaluate the tool with a survey, usability tests using think-aloud protocols, and semi-structured interviews. The results show that overall students find the tool easy to learn and are willing to use it in Visualization and other future courses. The evaluation transcripts are categorized and interpreted into themes with help of content analysis. This work also presents implications in design and implementation for future projects. / Division of Computational Science and Technology, KTH Royal Institute of Technology Detta arbete presenteras ett interaktivt visualiseringsverktyg för sökning av videoinnehåll för föreläsningsvideor i en flippade klassrummet-kurs Visualisering. Sökningen utförs med hjälp av videobildtexten med en sökmotor Lunr på klientsidan. Verktyget syftar till att förbättra tillgängligheten till kursens videomaterial och öka engagemanget i inlärningen, särskilt när eleverna ser videorna på nytt. Arbetet fokuserar på att använda en interaktiv visualiseringsmetod för att hjälpa användarna att förstå resultaten och söka videoklipp av intresse. Vi utvärderar verktyget med hjälp av en enkät, användbarhetstester med hjälp av Tänk–högt–metoden och semistrukturerade intervjuer. Resultaten visar att studenterna överlag tycker att verktyget är lätt att lära sig och är villiga att använda det i visualisering och andra framtida kurser. Utvärderingsutskrifterna kategoriseras och tolkas i teman med hjälp av innehållsanalys. Detta arbete presenteras också implikationer i utformning och genomförande för framtida projekt.

I dagens samhälle cirkulerar stora mängder av reklambudskap genom olika digitala kanaler, vilket ställer högre krav på företagen att producera innehåll som är relevant, av nytta och värdeskapande för mottagaren. Innehållet har alltså betydelsefull roll för att ens nå ut till mottagare, vilket har lett till att marknadsföringsstrategin content marketing har vuxit med stormsteg de senaste åren. Ett företag som har använt content marketing under många år och visat stor framgång inom det är Volvo Trucks, vilket är ett av studiens fallstudieobjekt. Skånetrafiken är en organisation som nyligen har implementerat content marketing strategin i sitt marknadsföringsarbete, vilket är studiens andra fallstudieobjekt. Syftet med studien är att uppnå en ökad förståelse kring hur Volvo Trucks och Skånetrafiken använder content marketing i sina reklamfilmer idag, för att sedan öka insikten i hur Skånetrafiken kan utveckla sina reklamfilmer utifrån Volvo Trucks.För att analysera Volvo Trucks och Skånetrafikens reklamfilmer har fem näranalyser genomförts; tre av Volvo Trucks och två av Skånetrafiken. Därefter har en visuell low-fidelity- prototyp tagits fram för att påvisa hur Skånetrafiken skulle kunna utveckla sina reklamfilmer enligt Volvo Trucks användning av content marketing. Studiens resultat visade på att genom en utveckling av det underliggande budskapet och en ökning av igenkänningsfaktorn kan detta främja den känslomässiga reaktionen hos mottagaren och på så vis kommunicera det underhållande värdet. Prototypen visualiserar ett vardagligt händelseförlopp som består av ett barn som huvudkaraktär, en familjär miljö och ett tydligare underliggande budskap för att förmedla både det informativa och underhållande värdet. / In today's society, large volumes of advertising messages are circulated through different digital channels, which places higher demands on companies to create relevant, useful and value content for the customer. The content has a significant role in reaching out to the customers, which has led to the increasing growth of the strategy Content marketing (shortened CM in the paper) in the last few years. One company that has used CM for many years and proved successful in this is Volvo Trucks, which is one of the case study objects in this paper. Skånetrafiken is an organization that has recently implemented CM in its marketing work, which also is the papers case study object. The purpose of the study is to gain an increased understanding of how Volvo Trucks and Skånetrafiken use content marketing in their commercials, and then to gain insight into how Skånetrafiken can develop their commercials based on Volvo Trucks.To investigate which values Volvo Trucks is communicating and how Skånetrafiken can develop and improve its use of CM, five visual content analysis using Nordströms (1989) method called Näranalys, has been implemented; three of Volvo Trucks and two of Skånetrafiken. Subsequently, a visual low-fidelity prototype has been developed that shows how Skånetrafiken could develop its campaign film "Door closing" according to Volvo Trucks use of CM. The study's results showed that through the development of the underlying message and an increase in the recognition factor, this can promote the emotional response of the customer. The prototype visualizes an everyday storyline that consists of a child as the main character, a familiar environment and a clearer underlying message to communicate both the informative and entertaining value.

No description available.

The importance of video content in Czech internet news has been steadily rising for almost two decades, media houses are creating and expanding separate video-making departments and investing in equipment needed for their creations. News websites place considerable emphasis on the production of their own audiovisual content, which has become so common that the reader has come to expect it. The work brings a comprehensive description and evaluation of the video content of three major Czech news sites: iDnes.cz, Novinky.cz and Aktuálně.cz. It describes the processes, techniques and tools used in video journalism and gives an overview of the video production of these three news sites and insight into the relevance of video for Czech online news. The practical part draws on a case study of the selected websites, which focuses on the individual editorial environment and their common practice. It includes a quantitative content analysis that answers the research question: "What is the current form of video content on news sites iDnes.cz, Novinky.cz and Aktuálně.cz?" The analysis is accompanied by interviews with experts from the field and my own experience. In my interviews, I asked questions, related to the theoretical part of this work, about the inner workings of editorial teams, their team strategy and source...

Video databases and content based retrieval in these databases have become popular with the improvements in technology. Metadata extraction techniques are used for providing data to video content. One popular metadata extraction technique for mul- timedia is information extraction from text. For some domains, it is possible to &amp / #64257 / nd accompanying text with the video, such as soccer domain, movie domain and news domain. In this thesis, we present an approach of metadata extraction from match reports for soccer domain. The UEFA Cup and UEFA Champions League Match Reports are downloaded from the web site of UEFA by a web-crawler. These match reports are preprocessed by using regular expressions and then important events are extracted by using hand-written rules. In addition to hand-written rules, two di&amp / #64256 / erent machine learning techniques are applied on match corpus to learn event patterns and automatically extract match events. Extracted events are saved in an MPEG-7 &amp / #64257 / le. A user interface is implemented to query the events in the MPEG-7 match corpus and view the corresponding video segments.

Subjective video quality and video decoding complexity are jointly optimized in order to determine the video encoding parameters that will result in the best Quality of Experience (QoE) for an end user watching a video clip on a mobile device. Subjective video quality is estimated by an objective criteria, video quality metric (VQM), and a method for predicting the video quality of a test sequence from the available training sequences with similar content characteristics is presented. Standardized spatial index and temporal index metrics are utilized in order to measure content similarity. A statistical approach for modeling decoding complexity on a hardware platform using content features extracted from video clips is presented. The overall decoding complexity is modeled as the sum of component complexities that are associated with the computation intensive code blocks present in state-of-the-art hybrid video decoders. The content features and decoding complexities are modeled as random parameters and their joint probability density function is predicted as Gaussian Mixture Models (GMM). These GMMs are obtained off-line using a large training set comprised of video clips. Subsequently, decoding complexity of a new video clip is estimated by using the available GMM and the content features extracted in real time. A novel method to determine the video decoding capacity of mobile terminals by using a set of subjective decodability experiments that are performed once for each device is also proposed. Finally, the estimated video quality of a content and the decoding capacity of a device are combined in a utility-complexity framework that optimizes complexity-quality trade-off to determine video coding parameters that result in highest video quality without exceeding the hardware capabilities of a client device. The simulation results indicate that this approach is capable of predicting the user viewing satisfaction on a mobile device.

The recently released High Efficiency Video Coding (HEVC) standard, which halves the transmission bandwidth requirement of encoded video for almost the same quality when compared to H.264/AVC, and the availability of increased network bandwidth (e.g. from 2 Mbps for 3G networks to almost 100 Mbps for 4G/LTE) have led to the proliferation of video streaming services. Based on these major innovations, the prevalence and diversity of video application are set to increase over the coming years. However, the popularity and success of current and future video applications will depend on the perceived quality of experience (QoE) of end users. How to measure or predict the QoE of delivered services becomes an important and inevitable task for both service and network providers. Video quality can be measured either subjectively or objectively. Subjective quality measurement is the most reliable method of determining the quality of multimedia applications because of its direct link to users’ experience. However, this approach is time consuming and expensive and hence the need for an objective method that can produce results that are comparable with those of subjective testing. In general, video quality is impacted by impairments caused by the encoder and the transmission network. However, videos encoded and transmitted over an error-prone network have different quality measurements even under the same encoder setting and network quality of service (NQoS). This indicates that, in addition to encoder settings and network impairment, there may be other key parameters that impact video quality. In this project, it is hypothesised that video content type is one of the key parameters that may impact the quality of streamed videos. Based on this assertion, parameters related to video content type are extracted and used to develop a single metric that quantifies the content type of different video sequences. The proposed content type metric is then used together with encoding parameter settings and NQoS to develop content-based video quality models that estimate the quality of different video sequences delivered over IP-based network. This project led to the following main contributions: (1) A new metric for quantifying video content type based on the spatiotemporal features extracted from the encoded bitstream. (2) The development of novel subjective test approach for video streaming services. (3) New content-based video quality prediction models for predicting the QoE of video sequences delivered over IP-based networks. The models have been evaluated using subjective and objective methods.