Social Documentary – a media artist installation in Istanbul imagining Linked Television in other ways

Social Documentary is an artistic installation to navigate in a collection of crowd-sourced videos which has been produced in collaboration with LinkedTV. Those videos are related to the events that happened at Gezi Park (Istanbul) in June 2013.

The visitors are invited to interact with the installation by choosing keywords through the manipulation of three cubes. Each cube represents a class of keywords (people, action, emotion). As the videos are cut into segments and tagged with the same keywords, the system will automatically choose the most relevant video according to the position of the cubes. A Kinect-based system allows us to track the two closest visitors’ faces and infer on their interest for the played video. The more the visitors are interested, the higher is the probability to display this video to the next visitors, like in recommendation system on video broadcast platforms. In this way, the installation evolves with its public. Some segments will emerge from the others as the “most popular”.

This video presents the public exhibit which completed a one week workshop that took place in August 2014, at BüyükAyi atelier, Istanbul. This workshop has boosted up the physical realisation of the project. In one week, the interaction table has been rebuilt from a former one coming from a previous BüyükAyi project, all the equipment has been included in it and the software parts have been upgraded. For example, a lot of filtering has been added to avoid false marker detection or loss of people tracking in the Interest Tracker software. The public presentation brought about twenty people to the BüyükAyi place, most of them were from artists’ circles but we also welcomed some tourists intrigued by the event. In general, the installation intrigued the visitors and they spent a few minutes playing with it. Some of them came to us with ideas to improve it; the most recurrent idea was to take a better advantage of the second screen. We will work on this direction by incorporating multimedia content coming from LinkedTV enrichment services.

The artists would like to present this installation in other places in Istanbul, like art galleries or museums and in conferences on human-machine interaction but no date has been set yet. Nevertheless, this installation should be easy to reproduce and all the sources are freely available on github (https://github.com/Zarfab/SocialDocumentary). We hope other people will build their own and present other type of multimedia content.

For further information, feel free to contact us:

Fabien Grisard : fabien.grisard@umons.ac.be

Tags: , ,
Posted in Uncategorized by lyndon.nixon@sti2.org. No Comments

How do we annotate TV programs and use annotations to link to related content? (#dwerft talk by @lyndonjbnixon)

Last week LinkedTV scientific co-ordinator Dr Lyndon Nixon spoke as invited speaker at the d-werft conference in Potsdam, Germany where he outlined the LinkedTV approach to annotating TV programming and using that annotation to generate links from parts of the TV programme to related content on the Web. Check out the slides below:

 

 

Tags: , , ,
Posted in News by lyndon.nixon@sti2.org. No Comments

LinkedTV presented improved results at the 2014 NIST #TRECVID Workshop for Multimedia Event Detection, Multimedia Event Recounting and Semantic Indexing

LinkedTV partner CERTH participated this year to the Semantic Indexing (SIN), Multimedia Event Detection (MED) and Multimedia Event Recounting (MER) tasks of the TRECVID International Benchmarking Activity. Significantly improved results were attained, compared to last year’s participation to the same tasks, verifying the significance of the work carried out in LinkedTV for solving hard video analysis problems.

One of the highlights of LinkedTV’s participation was the new, very fast machine learning method for big data problems that CERTH developed. Tested in large-scale multimedia event detection problems, this new method produces better results than both Kernel- and Linear-SVMs, while its training is one or two orders of magnitude faster than Linear-SVMs (and even more so compared to Kernel-SVMs). The use of this new approach in the Multimedia Event Detection problem was highlighted with an oral presentation at the TRECVID Workshop (check out our slides on this: http://www.iti.gr/~bmezaris/downloads/CERTH_TRECVID14_MED_Presentation.pdf ).

LinkedNews application @bid_dimad after winning Design Prize; will be exhibited in Madrid and then Latin America.

At the Ibero American Biennial of Design (BID) in Madrid, researchers Lilia Perez and Michiel Hildebrand from the Centrum Wiskunde & Informatica (CWI) in Amsterdam, have been awarded a honorary mention in the category Digital Design for the concept and interaction design of Linked TV News. Linked TV News is a second screen companion for watching the news based on semantic web technologies.  

The project was selected out of six hundred submissions and reached the top 5 in its category. As a consequence Linked TV News will be featured in the international exhibition of the Biennial that will be shown from 25 November 2014 to 28 February 2015 in Madrid. Following that, the collection will tour throughout Spain and several Latin American countries to be shown in design and art museums and venues.

See the LinkedTV News application design video:

LinkedTV News application design from Linked Television on Vimeo.

 

LinkedTV congratulates its partner CWI for this achievement!

Original news item from the CWI newswire. 

Posted in Uncategorized by lyndon.nixon@sti2.org. No Comments

@CERTH releases new version (V1.4) of their video temporal segmentation software for #videoanalysis

LinkedTV partner CERTH (Thessaloniki, Greece) just publicly released version 1.4 of its software for the automatic temporal segmentation of videos into shots and scenes. This release uses exclusively CPU-based processing and the analysis is accelerated by invoking multi-threading / multi-processing operations of the Intel OpenMP runtime library, making the whole video analysis process about 7 times faster than real-time processing on an i7 PC.

The development and release of this software was supported by EU research projects LinkedTV and MediaMixer (http://www.mediamixer.eu/). Read more about research on hypervideo analysis in LinkedTV as well as check out several video analysis demonstrators.

The software is available for download at http://mklab.iti.gr/project/video-shot-segm

Tags: , ,
Posted in News by lyndon.nixon@sti2.org. No Comments

Report from #MediaEval2014 – LinkedTV in Search & Hyperlinking of Multimedia Content

LinkedTV took part for the second time in the MediaEval Search and Hyperlinking task. The methodology developed by project partners produced interesting results which confirmed that LinkedTV Hyperlinking technologies are strong performers. More details on the LinkedTV approach are available here.

In MediaEval 2014, LinkedTV in collaboration with other research projects also supported the organization of the “Social Event Detection in Web Multimedia” (SED) task, and participated to the “Synchronization of Multi-user Event Media” (SEM) task, confirming in practice the project’s commitment to the evaluation of multimedia analysis and organization technologies through open benchmarking initiatives.

Tags: ,
Posted in News by lyndon.nixon@sti2.org. No Comments

#icip2014 #acmmm14 tutorial on Video Hyperlinking slides are online.

LinkedTV presented its tutorial on Video Hyperlinking at the International Conference on Image Processing held in Paris this year (27-30th Oct 2014) as well as ACM Multimedia in Orlando, Florida (USA) (3rd-7th Nov 2014).

The 3 hour tutorial  covered the topics of video analysis and hyperlink generation, building on the work carried out in LinkedTV’s work on those topics led by partners CERTH and EURECOM. The full slide set is available at LinkedTV’s Slideshare channel, and you can get started here:

 

Tags: ,
Posted in News Presentation by lyndon.nixon@sti2.org. No Comments

LinkedTV does #icip2014 tutorial on Video Hyperlinking, papers on video analysis and concept detection for cross modal multimedia search

LinkedTV is being well represented at the International Conference on Image Processing held in Paris this year (27-30th Oct 2014). ICIP is the premier conference on Image Processing attracting this year over 1500 attendees.

LinkedTV presented its tutorial on Video Hyperlinking on the opening day of the conference. The 3 hour tutorial was well attended and generated many interesting discussions. It covered the topics of Video Analysis and HyperLink generation, building on the work carried out in LinkedTV’s workpackages on those topics led by partners CERTH and EURECOM as well as on results obtained through the participation to various international benchmarking activities (MediaEval 2014 report coming soon).

Two LinkedTV research papers on “LINKING TEXT AND VISUAL CONCEPTS SEMANTICALLY FOR CROSS MODAL MULTIMEDIA SEARCH” and “NO-REFERENCE BLUR ASSESSMENT IN NATURAL IMAGES USING FOURIER TRANSFORM AND SPATIAL PYRAMIDS” were also presented during the main conference.

 

Posted in Uncategorized by lyndon.nixon@sti2.org. No Comments

#iswc2014 Tutorial “Remixing Media on the Semantic Web” – All slides now online!

Learn with LinkedTV about:

  • Media Fragment URI specification
  • Named Entity extraction
  • Open Annotation Model
  • The LinkedTV Ontology
  • Linked Media principles
  • Publishing and retrieving semantic multimedia metadata
  • Enrichment of video and TV with links
  • Browsing and linking media fragments
  • User expectations and experience with enriched video
  • The LinkedNews and LinkedCulture applications

The slides of our ISWC2014 tutorial “Remixing Media on the Semantic Web” are available directly from the event webpage.

Posted in Uncategorized by lyndon.nixon@sti2.org. No Comments

LinkedTV brings hypernym discovery to German #DBPedia! @DBpedia_De #lod #lhd #thd #ner

LinkedTV is pleased to contribute to the German DBPedia effort through the addition of hypernym discovery within Wikipedia article text. The “Linked Hypernyms Dataset” identifies the types of a resource through statistical type inference co-occurrence.

With this, a key problem for the German DBPedia dataset is being addressed: the sparsity of RDF type properties on DBPedia resources which makes SPARQL querying more difficult.

The new German DBPedia dataset now contains between 43 and 53% more rdf:type triples.

The same dataset is applied in the LinkedTV project to classify extracted entities from TV programming by type. This functionality is encapsulated in the service Targeted Hypernym Discovery (THD), developed and provided by our partner University of Economics Prague.

This was originally announced following the 2nd DBPedia Community meeting at http://de.dbpedia.org/node/30.

 

Tags: ,
Posted in Demos News by lyndon.nixon@sti2.org. No Comments