TREC 2002 video track experiments at MediaTeam Oulu and VTT

Mika Rautiainen; Jani Penttilä; Dmitri Vorobiev; Kai Noponen; Pertti Väyrynen; Matti Hosio; Esa Matinmikko; Satu-Marja Mäkelä; Johannes Peltola; Timo Ojala; Tapio Seppänen

TREC 2002 video track experiments at MediaTeam Oulu and VTT

Mika Rautiainen, Jani Penttilä, Dmitri Vorobiev, Kai Noponen, Pertti Väyrynen, Matti Hosio, Esa Matinmikko, Satu-Marja Mäkelä, Johannes Peltola, Timo Ojala, Tapio Seppänen

University of Oulu

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific

Abstract

In TREC 2002 Video Track MediaTeam Oulu and VTT Technical Research Centre of Finland participated jointly in semantic feature extraction, manual search and interactive search tasks. In the semantic feature extraction task, we sent results for semantic categories of cityscape, landscape, people, speech and instrumental sound. Spatio-temporal correlation of oriented gradient occurrences was used with example shots to detect shots containing people, cityscape or landscape. The audio signal features consisted of various statistical measurements and were used to detect shots containing speech or instrumental sound. Our video
browsing and retrieval system, VIRE, was used for manual and interactive search tasks. Our system offers two techniques for video retrieval: 1. Multi-modal indexing based on self-organizing feature maps with semantic filtering. 2. An interactive navigating tool that combines two inter-shot properties, temporal
coherency and metric similarities, into a view where database shots are presented in a lattice structure. We tested our interactive navigating tool with eight persons to obtain results for 25 pre-defined search topics. In this paper we give an overview of the approaches and a summary of the results.

Original language	English
Title of host publication	Text Retrieval Conference TREC 2002 Video Track
Number of pages	12
Publication status	Published - 2002
MoE publication type	B3 Non-refereed article in conference proceedings
Event	Text Retrieval Conference TREC 2002 Video Track - Gaithersburg, United States Duration: 19 Nov 2002 → 22 Nov 2002

Conference

Conference	Text Retrieval Conference TREC 2002 Video Track
Country/Territory	United States
City	Gaithersburg
Period	19/11/02 → 22/11/02

Access to Document

http://trec.nist.gov/pubs/trec11/papers/uoulu.rautiainen.pdf

Cite this

@inproceedings{71d71cc4c910492f8e807e6af18dfde3,

title = "TREC 2002 video track experiments at MediaTeam Oulu and VTT",

abstract = "In TREC 2002 Video Track MediaTeam Oulu and VTT Technical Research Centre of Finland participated jointly in semantic feature extraction, manual search and interactive search tasks. In the semantic feature extraction task, we sent results for semantic categories of cityscape, landscape, people, speech and instrumental sound. Spatio-temporal correlation of oriented gradient occurrences was used with example shots to detect shots containing people, cityscape or landscape. The audio signal features consisted of various statistical measurements and were used to detect shots containing speech or instrumental sound. Our videobrowsing and retrieval system, VIRE, was used for manual and interactive search tasks. Our system offers two techniques for video retrieval: 1. Multi-modal indexing based on self-organizing feature maps with semantic filtering. 2. An interactive navigating tool that combines two inter-shot properties, temporalcoherency and metric similarities, into a view where database shots are presented in a lattice structure. We tested our interactive navigating tool with eight persons to obtain results for 25 pre-defined search topics. In this paper we give an overview of the approaches and a summary of the results.",

author = "Mika Rautiainen and Jani Penttil{\"a} and Dmitri Vorobiev and Kai Noponen and Pertti V{\"a}yrynen and Matti Hosio and Esa Matinmikko and Satu-Marja M{\"a}kel{\"a} and Johannes Peltola and Timo Ojala and Tapio Sepp{\"a}nen",

year = "2002",

language = "English",

booktitle = "Text Retrieval Conference TREC 2002 Video Track",

note = "Text Retrieval Conference TREC 2002 Video Track ; Conference date: 19-11-2002 Through 22-11-2002",

}

Rautiainen, M, Penttilä, J, Vorobiev, D, Noponen, K, Väyrynen, P, Hosio, M, Matinmikko, E, Mäkelä, S-M , Peltola, J, Ojala, T & Seppänen, T 2002, TREC 2002 video track experiments at MediaTeam Oulu and VTT. in Text Retrieval Conference TREC 2002 Video Track. Text Retrieval Conference TREC 2002 Video Track, Gaithersburg, Maryland, United States, 19/11/02. <http://trec.nist.gov/pubs/trec11/papers/uoulu.rautiainen.pdf>

TY - GEN

T1 - TREC 2002 video track experiments at MediaTeam Oulu and VTT

AU - Rautiainen, Mika

AU - Penttilä, Jani

AU - Vorobiev, Dmitri

AU - Noponen, Kai

AU - Väyrynen, Pertti

AU - Hosio, Matti

AU - Matinmikko, Esa

AU - Mäkelä, Satu-Marja

AU - Peltola, Johannes

AU - Ojala, Timo

AU - Seppänen, Tapio

PY - 2002

Y1 - 2002

N2 - In TREC 2002 Video Track MediaTeam Oulu and VTT Technical Research Centre of Finland participated jointly in semantic feature extraction, manual search and interactive search tasks. In the semantic feature extraction task, we sent results for semantic categories of cityscape, landscape, people, speech and instrumental sound. Spatio-temporal correlation of oriented gradient occurrences was used with example shots to detect shots containing people, cityscape or landscape. The audio signal features consisted of various statistical measurements and were used to detect shots containing speech or instrumental sound. Our videobrowsing and retrieval system, VIRE, was used for manual and interactive search tasks. Our system offers two techniques for video retrieval: 1. Multi-modal indexing based on self-organizing feature maps with semantic filtering. 2. An interactive navigating tool that combines two inter-shot properties, temporalcoherency and metric similarities, into a view where database shots are presented in a lattice structure. We tested our interactive navigating tool with eight persons to obtain results for 25 pre-defined search topics. In this paper we give an overview of the approaches and a summary of the results.

AB - In TREC 2002 Video Track MediaTeam Oulu and VTT Technical Research Centre of Finland participated jointly in semantic feature extraction, manual search and interactive search tasks. In the semantic feature extraction task, we sent results for semantic categories of cityscape, landscape, people, speech and instrumental sound. Spatio-temporal correlation of oriented gradient occurrences was used with example shots to detect shots containing people, cityscape or landscape. The audio signal features consisted of various statistical measurements and were used to detect shots containing speech or instrumental sound. Our videobrowsing and retrieval system, VIRE, was used for manual and interactive search tasks. Our system offers two techniques for video retrieval: 1. Multi-modal indexing based on self-organizing feature maps with semantic filtering. 2. An interactive navigating tool that combines two inter-shot properties, temporalcoherency and metric similarities, into a view where database shots are presented in a lattice structure. We tested our interactive navigating tool with eight persons to obtain results for 25 pre-defined search topics. In this paper we give an overview of the approaches and a summary of the results.

M3 - Conference article in proceedings

BT - Text Retrieval Conference TREC 2002 Video Track

T2 - Text Retrieval Conference TREC 2002 Video Track

Y2 - 19 November 2002 through 22 November 2002

ER -

TREC 2002 video track experiments at MediaTeam Oulu and VTT

Abstract

Conference

Access to Document

Fingerprint

Cite this