Automated Information Extraction in Media Production最新文献

Session details: Media content structuring and indexing 会话细节:媒体内容结构和索引

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/3256249

A. Messina

引用次数: 0

Produce. annotate. archive. repurpose --: accelerating the composition and metadata accumulation of tv content 生产。注释。档案。Repurpose——加速电视内容的构成和元数据积累

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/2072552.2072560

R. Knauf, Jens Kürsten, Albrecht Kurze, M. Ritter, Arne Berger, Stephan Heinich, Maximilian Eibl

引用次数: 14

Sequence-based kernels for online concept detection in video 基于序列的视频在线概念检测方法

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/2072552.2072554

W. Bailer

{"title":"Sequence-based kernels for online concept detection in video","authors":"W. Bailer","doi":"10.1145/2072552.2072554","DOIUrl":"https://doi.org/10.1145/2072552.2072554","url":null,"abstract":"Kernel methods, e.g. Support Vector Machines, have been successfully applied to classification problems such as concept detection in video. In order to capture concepts and events with longer temporal extent, kernels for sequences of feature vectors have been proposed, e.g. based on temporal pyramid matching or sequence alignment. However, all these approaches need a temporal segmentation of the video, as the kernel is applied to the feature vectors of a segment. In (semi-)supervised training, this is not a problem, as the ground truth is annotated on a temporal segment. When performing online concept detection on a live video stream, (i) no segmentation exists and (ii) the latency must be kept as low as possible. Re-evaluating the kernel for each temporal position of a sliding window is prohibitive due to the computational effort. We thus propose variants of the temporal pyramid matching, all subsequences and longest common subsequence kernels, which can be efficiently calculated for a temporal sliding window. An arbitrary kernel function can be plugged in to determine the similarity of feature vectors of individual samples. We evaluate the proposed kernels on the TRECVID 2007 High-level Feature Extraction data set and show that the sliding window variants for online detection perform equally well or better than the segment-based ones, while the runtime is reduced by at least 30%.","PeriodicalId":280321,"journal":{"name":"Automated Information Extraction in Media Production","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130615154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

From audio recurrences to TV program structuring 从音频递归到电视节目结构

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/2072552.2072556

Alina Elma Abduraman, Sid-Ahmed Berrani, J. Rault, Olivier Le Blouch

引用次数: 4

News story clustering from both what and how aspects: using bag of word model and affinity propagation 从“什么”和“怎么”两个方面对新闻故事进行聚类:利用词包模型和亲和力传播

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/2072552.2072555

W. Chu, Chao-Chin Huang, Wen-Fang Cheng

引用次数: 4

Picture-in-picture copy detection using spatial coding techniques 使用空间编码技术的图中图复制检测

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/2072552.2072559

S. Purushotham, Q. Tian, C.-C. Jay Kuo

引用次数: 4

Session details: 2: Media production and retrieval systems and applications 会议详细内容:2:媒体制作和检索系统及应用

Automated Information Extraction in Media Production Pub Date : 2011-12-01 DOI: 10.1145/3256250

Sid-Ahmed Berrani

引用次数: 0

Technologies for next-generation multi-media libraries: the contentus project 下一代多媒体图书馆的技术:contentus项目

Automated Information Extraction in Media Production Pub Date : 2010-10-29 DOI: 10.1145/1877850.1877852

A. Heß

{"title":"Technologies for next-generation multi-media libraries: the contentus project","authors":"A. Heß","doi":"10.1145/1877850.1877852","DOIUrl":"https://doi.org/10.1145/1877850.1877852","url":null,"abstract":"An ever-growing amount of digitized content as well as \"born-digital\" content published online forces libraries and archives to integrate new data sources and align them with their existing collections. This is a challenging task, since multimedia content is inherently diverse and integrating metadata is often complex due to the different structures, qualities and reliabilities of available sources. The CONTENTUS project investigates new solutions for libraries and multimedia archives.\u0000 In this talk, I will present our approach towards an integrated solution for libraries, archives and other content holders that facilitate a seamless transition from raw digital data to a semantic multimedia search environment. We aim to provide a complete set of tools ranging from quality control for digitization, content and metadata integration, to access through a semantic multimedia search and browsing interface.\u0000 The CONTENTUS multimedia search interface will offer integrated searches for texts, images, audio and audiovisual content in a unified semantic user interface. Search queries can be narrowed and expanded in an exploratory fashion, search results can be refined by disambiguating entities and topics, and semantic relationships become not only apparent, but can be navigated as well.\u0000 When the metadata available is not sufficient to describe the content for the purpose of the semantic search, CONTENTUS can generate the relevant metadata through a variety of content analysis techniques. These largely automated processing steps identify, among other things, named entities such as persons, places and organizations in texts, audio transcripts and audiovisual media. This makes it possible to associate content with matching authority file entries and ultimately to insert it into a growing semantic knowledge network that can then be searched or explored as described above.","PeriodicalId":280321,"journal":{"name":"Automated Information Extraction in Media Production","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124527612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Automatic news recommendations via profiling 通过分析自动推荐新闻

Automated Information Extraction in Media Production Pub Date : 2010-10-29 DOI: 10.1145/1877850.1877863

E. Mannens, Sam Coppens, Toon De Pessemier, Hendrik Dacquin, D. V. Deursen, R. Walle

{"title":"Automatic news recommendations via profiling","authors":"E. Mannens, Sam Coppens, Toon De Pessemier, Hendrik Dacquin, D. V. Deursen, R. Walle","doi":"10.1145/1877850.1877863","DOIUrl":"https://doi.org/10.1145/1877850.1877863","url":null,"abstract":"Today, people have only limited, valuable leisure time at their hands which they want to fill in as good as possible according to their own interests, whereas broadcasters want to produce and distribute news items as fast and targeted as possible. These (developing) news stories can be characterised as dynamic, chained, and distributed events in addition to which it is important to aggregate, link, enrich, recommend, and distribute these news event items as targeted as possible to the individual, interested user. In this paper, we show how personalised recommendation and distribution of news events, described using an RDF/OWL representation of the NewsML-G2 standard, can be enabled by automatically categorising and enriching news events metadata via smart indexing and linked open datasets available on the web of data. The recommendations - based on a global, aggregated profile, which also takes into account the (dis)likings of peer friends - are finally fed to the user via a personalised RSS feed. As such, the ultimate goal is to provide an open, user-friendly recommendation platform that harnesses the end-user with a tool to access useful news event information that goes beyond basic information retrieval. At the same time, we provide the (inter)national community with standardised mechanisms to describe/distribute news event and profile information.","PeriodicalId":280321,"journal":{"name":"Automated Information Extraction in Media Production","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126226811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Generic architecture for event detection in broadcast sports video 广播体育视频事件检测的通用体系结构

Automated Information Extraction in Media Production Pub Date : 2010-10-29 DOI: 10.1145/1877850.1877865

C. Poppe, S. D. Bruyne, R. Walle

引用次数: 10