Automatic Metadata Extraction

                                Marco Bertini
                         Università di Firenz...
The problem

                 The massive increase in digital audio-visual information
                 poses high demands...
Two solutions




             www.vidivideo.info     www.im3i.eu



giovedì 24 giugno 2010
VidiVideo: project overview
                     The VidiVideo project addressed the
                     challenge of cre...
VidiVideo: project results
           The automatic annotation part of the system performs audio
           and video segm...
Call Identifier FP7-SME-2010-1
   Submitted 03 December 2009



                   VidiVideo: project partners
   Name of ...
IM3I: project overview
                  IM3I aims to provide the creative media sector with new
                  ways of...
IM3I: project results
            Developed a set of tools for automatic audio-visual
            annotation and search
  ...
IM3I: project partners




giovedì 24 giugno 2010
The VidiVideo backend




giovedì 24 giugno 2010
Video and scene segmentation
 •Developed a new gradual transition detection algorithm
 •Uses novel individual criteria tha...
Audio analysis in VidiVideo
                 • Audio segmentation / audio diarization
                 • Audio events dete...
Block diagram of audio processing
                                                                                        ...
Audio events corpora
                 •       Sound effect corpus: 18,700 short files (290 hrs.),
                         ...
Machine learning
                 •       Learning of many independent binary classification
                         tasks...
Color Features




                         Point sampling     Color Descriptor
                         • Harris-Laplace ...
0.25
                                               Results
                          MediaMill Semantic Video Search Engi...
The IM3I backend




giovedì 24 giugno 2010
Visual annotation
                 •       Split a video detecting shots and large content changes
                       ...
Baseline: typical BoW

                                            Hierarch.
                                            c...
Fusion schemes




   •       Early fusion: integrates unimodal features before learning concepts.

   •       Late fusion...
Fusion schemes




   •       Early fusion: integrates unimodal features before learning concepts.

   •       Late fusion...
Early fusion approach


                                                                                   Hierarch.
     ...
Late fusion approach
                                                                                                     ...
Test: baseline
                                                                       Time       Avg.       Max
          ...
Test: early fusion
                               Sampling                                               Avg.          Max...
Test: late fusion
                   Method 1           Method 2                                Accuracy




             ...
Conclusions
         •       Early fusion strategies:
               •   ~ baseline accuracy
               •   faster
   ...
The users



giovedì 24 giugno 2010
Video search engine
                Our goal is to provide a search engine for videos
                for both technical a...
Sirio and Orione
                                    •   Design goals/assumptions:

                                      ...
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Sirio and Orione




giovedì 24 giugno 2010
Andromeda
                                                          •   System interface query options:
       •       Des...
Andromeda




giovedì 24 giugno 2010
Andromeda




giovedì 24 giugno 2010
Andromeda




giovedì 24 giugno 2010
Andromeda




giovedì 24 giugno 2010
Andromeda




giovedì 24 giugno 2010
Andromeda




giovedì 24 giugno 2010
Pan
                •        Design goals/assumptions:

                         •   complete/correct automatic
          ...
Pan




                               !
giovedì 24 giugno 2010
Pan




                               !
giovedì 24 giugno 2010
Pan




                               !
giovedì 24 giugno 2010
Pan




                               !
giovedì 24 giugno 2010
Pan




giovedì 24 giugno 2010
Pan




giovedì 24 giugno 2010
Daphnis
        •       Design goals/assumptions:

              •          build on image tagging made popular     •   Sy...
Daphnis




                                   !

giovedì 24 giugno 2010
Daphnis




giovedì 24 giugno 2010
Daphnis




                                   !

giovedì 24 giugno 2010
Daphnis




giovedì 24 giugno 2010
IM3I: authoring platform
            A CMS approach to repository
           analysis, authoring and publication



gioved...
IM3I: authoring platform
                     Authoring IM3I end-user functionality typically covers 5
                   ...
Editing workflow demo
                         •Step 1: Importing a video-repository
                         •Step 2: Enha...
I: Importing a repository

               •Importing an existing repository to an internal and
               flexible data...
I: Importing a repository

                                            Mapping the
                                       ...
II: Enhancing the Datamodel
                         •Datamodels contain the descriptions of your
                        ...
II: Enhancing the Datamodel




                     Adding a ‘translation’ element to the datamodel
giovedì 24 giugno 2010
II: Enhancing the Datamodel




                     Adding a ‘translation’ element to the datamodel
giovedì 24 giugno 2010
III: Layout and Functionality
                     Easy manipulation of layout to a repository by:

                      ...
III: Layout and Functionality




                     Defining a layout table
giovedì 24 giugno 2010
III: Layout and Functionality




                     Dragging repository contents to layout
giovedì 24 giugno 2010
III: Layout and Functionality




                     Previewing layout
giovedì 24 giugno 2010
IV: Embedding in website

                         Easy blend- in of layouts in corporate websites

                      ...
IV: Embedding in website



              Original
              contents                    Added
                       ...
The super users



giovedì 24 giugno 2010
Atlante - process manager
                                                 •   Main functions of this
     •       Web app...
Atlante




                                   !

giovedì 24 giugno 2010
Atlante




                                   !

giovedì 24 giugno 2010
Atlante




                                   !

giovedì 24 giugno 2010
Gaia - media manager

                 •       Web application that will be used for a technical
                         ...
Gaia




                                !
giovedì 24 giugno 2010
Gaia




                                !


giovedì 24 giugno 2010
One more thing...



giovedì 24 giugno 2010
giovedì 24 giugno 2010
giovedì 24 giugno 2010
ACM MM 2010 Workshop
        3rd International Workshop on Automated Information Extraction in Media Production
          ...
“Sirio” R.I.A. search engine demo




giovedì 24 giugno 2010
“Sirio” R.I.A. search engine demo




giovedì 24 giugno 2010
Web-based R.I.A. archive browsing




giovedì 24 giugno 2010
Web-based R.I.A. archive browsing




giovedì 24 giugno 2010
Upcoming SlideShare
Loading in …5
×

Bertini - Automatic Metadata Extraction in VidiVideo & im3i @EUscreen Mykonos

1,538 views
1,478 views

Published on

Published in: Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
1,538
On SlideShare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
25
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Bertini - Automatic Metadata Extraction in VidiVideo & im3i @EUscreen Mykonos

  1. 1. Automatic Metadata Extraction Marco Bertini Università di Firenze - MICC www.micc.unifi.it giovedì 24 giugno 2010
  2. 2. The problem The massive increase in digital audio-visual information poses high demands on advanced storage and search engines for consumers and professional archives. Video is now a natural form of communication for the Internet and mobile devices. Video search engines are the product of progress in many technologies: visual and audio analysis, machine learning techniques, as well as visualization and interaction. giovedì 24 giugno 2010
  3. 3. Two solutions www.vidivideo.info www.im3i.eu giovedì 24 giugno 2010
  4. 4. VidiVideo: project overview The VidiVideo project addressed the challenge of creating a substantially enhanced semantic access to video, implemented in a search engine. The outcome of the project is an audio-visual search engine, composed of two parts: a automatic annotation part, that runs off-line, where detectors for more than 1000 semantic concepts are collected in a thesaurus to process and automatically annotate the video and an interactive part that provides a video search engine for both technical and non-technical users. giovedì 24 giugno 2010
  5. 5. VidiVideo: project results The automatic annotation part of the system performs audio and video segmentation, speech recognition, speaker clustering and semantic concept detection. The VidiVideo system has achieved the highest performance in the most important object and concept recognition international contests (PASCAL VOC and TRECVID). The interactive part provides a desktop-based and a web-based search engines. The system permits different query modalities (free text, natural language, graphical composition of concepts using boolean and temporal relations and query by visual example) and visualizations for video retrieval and browsing. giovedì 24 giugno 2010
  6. 6. Call Identifier FP7-SME-2010-1 Submitted 03 December 2009 VidiVideo: project partners Name of the co-ordinating person Dr.-Ing. Georgios Ioannidis E-Mail gi@in-two.com Fax +49-179-33-2286677 No. Participant Name Type Short Name Country 1 IN2 search interfaces development Ltd SME IN2 UK 2 spring techno GmbH SME SPRING DE 3 VISup Srl SME VISUP IT 4 Hogeschool voor de Kunsten Utrecht RTDP HKU NL 5 University Firenze RTDP UNIFI IT 6 Instituto de Engenharia de Sistemas e RTDP INESC-ID PT Computadores giovedì 24 giugno 2010
  7. 7. IM3I: project overview IM3I aims to provide the creative media sector with new ways of searching, summarising and visualising large multimedia archives. IM3I will provide a service-oriented architecture that allow multiple viewpoints upon multimedia data that are available in a repository, and provide better ways to interact and share rich media. This paves the way for a multimedia information management platform which is more flexible, adaptable and customisable than current repository software. This in turn enables new opportunities for content owners to exploit their digital assets. giovedì 24 giugno 2010
  8. 8. IM3I: project results Developed a set of tools for automatic audio-visual annotation and search Developed a set of web services to manage, create and orchestrate the indexing services Developed a set of specialized search and management interfaces IM3I authoring platform: allows professional users to import and publish repositories of digital media, authoring of web-based environments for the end-users, creation of elaborate workflow patterns and search & retrieval interfaces to allow a diversity of end-user interactions and scenarios giovedì 24 giugno 2010
  9. 9. IM3I: project partners giovedì 24 giugno 2010
  10. 10. The VidiVideo backend giovedì 24 giugno 2010
  11. 11. Video and scene segmentation •Developed a new gradual transition detection algorithm •Uses novel individual criteria that exhibit less sensitivity to local or global motion: •Color Coherence Change •Macbeth Color Histogram Change •Luminance Center of Gravity Change •Combines these criteria (and their multi-scale extensions) using a machine learning technique •Advantages: •Significantly improved performance •Lack of need for any threshold selection Scene or story unit: collection of temporally consecutive shots which are about the same topic or event •Developed a multimodal scene segmentation based on Scene Transition Graph • Significantly improved performance over visual-only STG giovedì 24 giugno 2010
  12. 12. Audio analysis in VidiVideo • Audio segmentation / audio diarization • Audio events detection (AED) • Automatic speech recognition (ASR) • Language identification (LID) giovedì 24 giugno 2010
  13. 13. Block diagram of audio processing Current Audio event detection framework Concept Detectors s Non Speech Feature extraction Feature Reductio SVM classification AE 61 AE + n 10 Sports (testing) Audio Segmentatio Speech Speech 6 Speech n Speaker ID Reasoning Narrator, 3 Monologue Anchor … Dialogue Audio Music Data Detector Music 3 Classes (base) 4 New (testing) Telephone Low 1 Telephone detector Frequenc y Detector Audio -------------- Processing Total 74+10 (testing) Video Processing Audio + Video +(-3+4) (change music detectors) giovedì 24 giugno 2010
  14. 14. Audio events corpora • Sound effect corpus: 18,700 short files (290 hrs.), provided by B&G. Intrinsically labelled corpus. • Selection of subset for training 61 semantic concepts with more examples. • Extended feature set: MFCCs, ZCR, Brightness / Audio spectrum centroid, Bandwidth / Audio spectrum spread Audio spectrum envelope, Audio spectrum flatness, Pitch, Harmonicity • Tested on Movies, Documentaries, Broadcast News, and Talk Shows (TS). • Mean Average Precision=0.459 (6 test concepts) giovedì 24 giugno 2010
  15. 15. Machine learning • Learning of many independent binary classification tasks is computationally expensive • KDA using Spectral Regression to solve this problem: • The time complexity scales linearly with respect to number of labels (i.e. concepts) • Training in just 1.3 hours compared to 30.2 hours using SVM, over 20 times faster! (MAP ~ the same) • Tested on Pascal VOC 2008 (20 Concepts) • Best Method in Pascal VOC 2008 • Ranked First in 9 out of 20 concepts giovedì 24 giugno 2010
  16. 16. Color Features Point sampling Color Descriptor • Harris-Laplace • SIFT • Dense sampling • OpponentSIFT • WSIFT Spatial Pyramid • rgSIFT • 1x1 • Transformed color SIFT • 2x2 • 1x3 giovedì 24 giugno 2010
  17. 17. 0.25 Results MediaMill Semantic Video Search Engine at TRECVID 2009 216 other concept detection methods Our results MediaMill concept detection method 0.2 0.15 TRECVid 2009 0.1 0.05 0 0 20 40 60 80 100 120 140 160 180 200 220 Concept Detection Task Submissions •Good local descriptors: SIFT, OpponentSIFT, rgSIFT/WSIFT, 0.25 Transformed color SIFT 0.2 22 users of other video retrieval systems 2 users of MediaMill video search engine •Combining these color features gives state-of-the-art 0.15 performance •Drawback: computational costs, reduced adopting GPU 0.1 0.05 implementations (codebook creation is 80% of CPU time!) for 17x speed-up 0 0 5 10 15 Interactive Search Task Submissions 20 25 giovedì 24 giugno 2010
  18. 18. The IM3I backend giovedì 24 giugno 2010
  19. 19. Visual annotation • Split a video detecting shots and large content changes with very fast algorithm • Use different annotation strategies and types of detectors: • low level (color, B/W, motion) • Haar-based boosted classifiers • HOG + SVMs • Bag-of-words • k-NN + voting • simple MPEG-7 XML format (full and fragment) giovedì 24 giugno 2010
  20. 20. Baseline: typical BoW Hierarch. clustering Feature extract. visual words histo Learning giovedì 24 giugno 2010
  21. 21. Fusion schemes • Early fusion: integrates unimodal features before learning concepts. • Late fusion: first reduces unim. feat. to separately learned concepts scores, then these scores are integrated to learn concepts. giovedì 24 giugno 2010
  22. 22. Fusion schemes • Early fusion: integrates unimodal features before learning concepts. • Late fusion: first reduces unim. feat. to separately learned concepts scores, then these scores are integrated to learn concepts. giovedì 24 giugno 2010
  23. 23. Early fusion approach Hierarch. clustering • Hypothesis: MSER isolate semantically relevant information. • Idea: represent points that have some spatial relation with regions that are inside, outside, just on the border • Sampling: SIFT-SURF, dense. giovedì 24 giugno 2010
  24. 24. Late fusion approach Hierarch. clustering Hierarch. clustering !"# !1 !2 !"###$%#&'%(!")#*%+,$-#&'-(!")#*%+......$%#&'%(!")#*/+,$-#&'-(!")#*/+# • Use SURF/SIFT + MSER • Use geometric descriptors for MSERs giovedì 24 giugno 2010
  25. 25. Test: baseline Time Avg. Max Method Sampling # points Time accuracy accuracy • Best: SURF 64 Grid 10 (accuracy, computational cost) • SURF 64 Grid 5: +7-8% accuracy, +300% time • the number of points influences accuracy giovedì 24 giugno 2010
  26. 26. Test: early fusion Sampling Avg. Max Method # points Time Time accuracy accuracy • Best: EF SURF 64 Grid 10 (accuracy, computational cost) • EF SURF 64 Borders: many points, accuracy ~ that of Grid 10 but higher computational costs • EF SURF 64 Grid 10 is worst than SURF 64 Grid 10, but much faster (50% of execution time) giovedì 24 giugno 2010
  27. 27. Test: late fusion Method 1 Method 2 Accuracy • weighting 0.6 (best method) and 0.4 (worst method) lead to good results • best performance: dense sampling + sparse sampling • best combination: SURF 64 + EF SURF 64 Grid 10 (improved accuracy, modest computational cost increase) giovedì 24 giugno 2010
  28. 28. Conclusions • Early fusion strategies: • ~ baseline accuracy • faster • Late fusion strategies: • better accuracy than baseline • each method corrects some errors made by the other • fuse keypoints/regions (SURF, fusion of SURF and MSER) • IM3I users will be able to chose what’s best for them giovedì 24 giugno 2010
  29. 29. The users giovedì 24 giugno 2010
  30. 30. Video search engine Our goal is to provide a search engine for videos for both technical and non-technical users. Provide different interfaces that permit different query modalities: free-text, natural language, graphical composition of concepts using boolean and temporal relations and query by visual example. In addition, exploit ontologies and their structure to encode semantic relations between concepts permitting, for example, to expand queries to synonyms and concept specializations. giovedì 24 giugno 2010
  31. 31. Sirio and Orione • Design goals/assumptions: • semantic content-based retrieval • efficient web-based interface • System features: • System interface query options: • Sirio is a Rich Internet • ontology exploration using a Application (in Adobe Flex) front graph-based view end. • compact keyframe-based results • Orione is web service search engine presentation / streaming videos • Support for multiple ontologies • concept drag&drop facility (to build and ontology reasoning complex queries) • Results are in Media RSS format • natural language query (with Boolean/ (queries treated as RSS feeds) temporal ops.) • New search engine able to scale • free text query (for Google-like to large number of instances of search) ontology concepts giovedì 24 giugno 2010
  32. 32. Sirio and Orione giovedì 24 giugno 2010
  33. 33. Sirio and Orione giovedì 24 giugno 2010
  34. 34. Sirio and Orione giovedì 24 giugno 2010
  35. 35. Sirio and Orione giovedì 24 giugno 2010
  36. 36. Sirio and Orione giovedì 24 giugno 2010
  37. 37. Sirio and Orione giovedì 24 giugno 2010
  38. 38. Sirio and Orione giovedì 24 giugno 2010
  39. 39. Sirio and Orione giovedì 24 giugno 2010
  40. 40. Andromeda • System interface query options: • Design goals/assumptions: • Shows the concepts with more instances in a concept cloud view • semantic content-based browsing • efficient web-based interface using • Graph representation of semantic data structure RIA • System features: • Multiple automatic layout algorithms for spatial positioning and manual drag • Query manager as a Rich Internet & drop Application (in Adobe Flex). Connects to web service (search • Thumbnails view of the instances of each concept engine) • Support for multiple ontologies • Access to video metadata and video streaming and ontology reasoning • Access to social content related to ontology concepts (Flickr,YouTube, and real time tweets from Twitter) giovedì 24 giugno 2010
  41. 41. Andromeda giovedì 24 giugno 2010
  42. 42. Andromeda giovedì 24 giugno 2010
  43. 43. Andromeda giovedì 24 giugno 2010
  44. 44. Andromeda giovedì 24 giugno 2010
  45. 45. Andromeda giovedì 24 giugno 2010
  46. 46. Andromeda giovedì 24 giugno 2010
  47. 47. Pan • Design goals/assumptions: • complete/correct automatic annotations • System interface options • help in training new automatic • Integrated with web-based concept detectors search engine and automatic • System features: video annotation • Rich Internet Application • Multiple user profiles: a (in Adobe Flex). simple user may change his own annotations, while a super user • video streaming using the same can import the annotations of system of Sirio and Andromeda other users, e.g. to supervise the annotation process • new backend within an organization. • geotagging using Google Maps giovedì 24 giugno 2010
  48. 48. Pan ! giovedì 24 giugno 2010
  49. 49. Pan ! giovedì 24 giugno 2010
  50. 50. Pan ! giovedì 24 giugno 2010
  51. 51. Pan ! giovedì 24 giugno 2010
  52. 52. Pan giovedì 24 giugno 2010
  53. 53. Pan giovedì 24 giugno 2010
  54. 54. Daphnis • Design goals/assumptions: • build on image tagging made popular • System interface options by Flickr and tag clouds • users can tag images and retrieve images based on tags, or use tags • connect to social web sites to filter the results of similarity based retrieval. • allow CBIR • System features: • Ongoing work: • Rich Internet Application • merging with automatic video annotation for automatic (in Adobe Flex). tagging • Connects to Flickr (and also • adoption of mechanisms for Facebook, if needed) tag suggestion, based on • Approximate nearest recent research work in this field (use content, tags and neighbour search using MPEG-7 descriptors, to scale to large number geolocalization) of images giovedì 24 giugno 2010
  55. 55. Daphnis ! giovedì 24 giugno 2010
  56. 56. Daphnis giovedì 24 giugno 2010
  57. 57. Daphnis ! giovedì 24 giugno 2010
  58. 58. Daphnis giovedì 24 giugno 2010
  59. 59. IM3I: authoring platform A CMS approach to repository analysis, authoring and publication giovedì 24 giugno 2010
  60. 60. IM3I: authoring platform Authoring IM3I end-user functionality typically covers 5 distinctive stages: • Importing an existing repository from RSS and various XML streams • Extending the associated datamodel • Editing layout and editing features • Editing Search and Retrieval interfaces • Embedding the IM3I end-user interfaces in a (corporate) website giovedì 24 giugno 2010
  61. 61. Editing workflow demo •Step 1: Importing a video-repository •Step 2: Enhancing the datamodel •Step 3: Authoring layouts •Step 4: Publishing the repository giovedì 24 giugno 2010
  62. 62. I: Importing a repository •Importing an existing repository to an internal and flexible datamodel •Aggregating and harmonizing multiple repositories •Visualisation of markup and preview of contents •Flexibly mapping by drag-and-drop giovedì 24 giugno 2010
  63. 63. I: Importing a repository Mapping the contents of video RSS to an IM3I Datamodel giovedì 24 giugno 2010
  64. 64. II: Enhancing the Datamodel •Datamodels contain the descriptions of your repository and in this way stipulate what can be shown to- or retrieved by an end-user. •Datamodels can reference to each other •Datamodels can be extended overtime by adding elements •Elements are based on types: media files, URIs, date, string, etc. •Elements can be shared across datamodels to allow search & retrieval across multiple collections giovedì 24 giugno 2010
  65. 65. II: Enhancing the Datamodel Adding a ‘translation’ element to the datamodel giovedì 24 giugno 2010
  66. 66. II: Enhancing the Datamodel Adding a ‘translation’ element to the datamodel giovedì 24 giugno 2010
  67. 67. III: Layout and Functionality Easy manipulation of layout to a repository by: •Table metaphor (easy editing of table characteristics) •Drag and drop graphical elements •Drag and drop contents of repository in cells •Easy manipulation of look and feel •Easy adding editing functionalities to a layout •Easy preview and markup functionalities giovedì 24 giugno 2010
  68. 68. III: Layout and Functionality Defining a layout table giovedì 24 giugno 2010
  69. 69. III: Layout and Functionality Dragging repository contents to layout giovedì 24 giugno 2010
  70. 70. III: Layout and Functionality Previewing layout giovedì 24 giugno 2010
  71. 71. IV: Embedding in website Easy blend- in of layouts in corporate websites •By means of plugins for CMSs (e.g. Webmanager, WordPress, Typo3) •By <embed> </embed> •Allowing for elaborate workflow patterns in combining multiple layouts giovedì 24 giugno 2010
  72. 72. IV: Embedding in website Original contents Added Translation Functionality giovedì 24 giugno 2010
  73. 73. The super users giovedì 24 giugno 2010
  74. 74. Atlante - process manager • Main functions of this • Web application that is used for application are: creation, technical administration and monitoring • creation of new type of of IM3I processing pipeline (e.g. (distributed) process automatic annotation process, media transcoding, etc.) • params setting for new type of process • This web application has • creation of “Multiprocess” multiple user profile: composed by sets of single • managers (distributed) Processes • administrators • starting/pausing/stopping a process • monitoring running processes giovedì 24 giugno 2010
  75. 75. Atlante ! giovedì 24 giugno 2010
  76. 76. Atlante ! giovedì 24 giugno 2010
  77. 77. Atlante ! giovedì 24 giugno 2010
  78. 78. Gaia - media manager • Web application that will be used for a technical administration and monitoring of the database • Main functions of this application are: • media management • configuration of metadata, broadcasters, Annotations types, Concept types and Media types • media annotations monitoring by technical backend giovedì 24 giugno 2010
  79. 79. Gaia ! giovedì 24 giugno 2010
  80. 80. Gaia ! giovedì 24 giugno 2010
  81. 81. One more thing... giovedì 24 giugno 2010
  82. 82. giovedì 24 giugno 2010
  83. 83. giovedì 24 giugno 2010
  84. 84. ACM MM 2010 Workshop 3rd International Workshop on Automated Information Extraction in Media Production AIEMPro'10 Organizers: Dr. Robbie De Sutter Vlaamse Radio- en Televisieomroep - Medialab Jean-Pierre Evain European Broadcasting Union . Union Européenne de Radiotélévision Dr. Gerald Friedland ICSI (International Computer Science Institute) Dr. Alberto Messina RAI Radiotelevisione Italiana, Centre for Research and Technological Innovation Dr. Masanori Sano NHK (Japan Broadcasting Corporation) Science and Technology Research Laboratories giovedì 24 giugno 2010
  85. 85. “Sirio” R.I.A. search engine demo giovedì 24 giugno 2010
  86. 86. “Sirio” R.I.A. search engine demo giovedì 24 giugno 2010
  87. 87. Web-based R.I.A. archive browsing giovedì 24 giugno 2010
  88. 88. Web-based R.I.A. archive browsing giovedì 24 giugno 2010

×