Vidi-Video (Interactive semantic video search with a large thesaurus of machine learned audio-visual concepts): Difference between revisions
From HLT@INESC-ID
m (Add a video demo URL) |
|||
(7 intermediate revisions by 2 users not shown) | |||
Line 1: | Line 1: | ||
{{TOCright}} | {{TOCright}} | ||
Funded by: EC VI Framework programme <br/> | '''Funded by:''' EC VI Framework programme<br/> | ||
Start date: | '''Start date:''' 01 February 2007<br/> | ||
Duration: 36 months | '''Duration:''' 36 months | ||
== Summary == | == Summary == | ||
VIDI-Video project takes on the challenge of creating a substantially enhanced semantic access to video, implemented in a search engine. The engine will boost the performance of video search by forming a 1000 element thesaurus detecting instances of audio, visual or mixed-media content. | The VIDI-Video project takes on the challenge of creating a substantially enhanced semantic access to video, implemented in a search engine. The engine will boost the performance of video search by forming a 1000 element thesaurus detecting instances of audio, visual or mixed-media content. | ||
== Partners == | == Partners == | ||
UvA - Universiteit van Amsterdam, the Netherlands (coordinator) | * UvA - Universiteit van Amsterdam, the Netherlands (coordinator) | ||
UNIS - University of Surrey, UK | * UNIS - University of Surrey, UK | ||
UNIFI – Universita degli Studi di Firenze, Italy | * UNIFI – Universita degli Studi di Firenze, Italy | ||
INESC-ID – Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal | * INESC-ID – Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal | ||
CERTH – Centre for Research and Technology Hellas, Greece | * CERTH – Centre for Research and Technology Hellas, Greece | ||
CVC – Centroi de Vision por Computador, Spain | * CVC – Centroi de Vision por Computador, Spain | ||
B&G – Stichting Netherlands Instituut voor Beeld & Geluid, the Netherlands | * B&G – Stichting Netherlands Instituut voor Beeld & Geluid, the Netherlands | ||
FRD - Fondazione Rinascimento Digitale, Italy Subcontracting | * FRD - Fondazione Rinascimento Digitale, Italy Subcontracting | ||
UoM - University of Modena e Reggio Emília, Italy | * UoM - University of Modena e Reggio Emília, Italy | ||
IIT – Indian Institute of Technology, India | * IIT – Indian Institute of Technology, India | ||
== INESC-ID main researchers == | == INESC-ID main researchers == | ||
Line 34: | Line 34: | ||
== Application scenarios == | == Application scenarios == | ||
Broadcast news | * Broadcast news | ||
Cultural heritage | * Cultural heritage | ||
* Surveillance | |||
== Demo == | |||
See the [https://www.youtube.com/watch?v=74Yluq9lVhQ youtube video]. | |||
== See Also == | |||
* [http://cordis.europa.eu/ist/kct/vidivideo_synopsis.htm Official CORDIS website] | |||
[[category:Research]] | |||
[[category:Projects]] | |||
[[category:International Projects]] |
Latest revision as of 16:52, 3 June 2020
Funded by: EC VI Framework programme
Start date: 01 February 2007
Duration: 36 months
Summary
The VIDI-Video project takes on the challenge of creating a substantially enhanced semantic access to video, implemented in a search engine. The engine will boost the performance of video search by forming a 1000 element thesaurus detecting instances of audio, visual or mixed-media content.
Partners
- UvA - Universiteit van Amsterdam, the Netherlands (coordinator)
- UNIS - University of Surrey, UK
- UNIFI – Universita degli Studi di Firenze, Italy
- INESC-ID – Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal
- CERTH – Centre for Research and Technology Hellas, Greece
- CVC – Centroi de Vision por Computador, Spain
- B&G – Stichting Netherlands Instituut voor Beeld & Geluid, the Netherlands
- FRD - Fondazione Rinascimento Digitale, Italy Subcontracting
- UoM - University of Modena e Reggio Emília, Italy
- IIT – Indian Institute of Technology, India
INESC-ID main researchers
Description
The project will apply machine learning techniques to learn many different detectors from examples, using active one-class classifiers to minimize the need for annotated examples. The project approach is to let the system learn many, possibly weaker detectors describing different aspects of the video content instead of modeling a few of them carefully. The combination of many detectors will render a much richer basis for the semantics. The integration of audio and video analysis is essential for many types of search concepts.
Application scenarios
- Broadcast news
- Cultural heritage
- Surveillance
Demo
See the youtube video.