video

ITI CERTH at TRECVID 2012

A Moumtzidou, N. Gkalelis, P. Sidiropoulos, M. Dimopoulos, S. Nikolopoulos, S. Vrochidis, V. Mezaris, I. Kompatsiaris,  "ITI-CERTH participation to TRECVID 2012", in Proceedings of TRECVID 2012 Workshop, November 2012, Gaithersburg, MD, USA.

Succesful participation of CERTH-ITI in interactive known-item video search of TRECVID 2012

CERTH-ITI participated to the Known-Item Search (KIS) Task of TRECVID 2012 with the interactive video retrieval engine VERGE. VERGE results achieved the second place, among the submissions made by all institutions participating to TRECVID 2012 KIS task (19 runs from 5 different institutions) with interactive systems. The latest version of VERGE supports advanced retrieval functionalities including visual similarity search, visual concept-based retrieval, video similarity based on PLSA and full text search, as well as two different representations (i.e. shot and video based). More information about VERGE is available here. Feel free to try on line the latest version of VERGE and search in the TRECVID 2012 KIS test data collection.

Local Invariant Feature Tracks for High-Level Video Feature Extraction

V. Mezaris, A. Dimou, I. Kompatsiaris, "Local Invariant Feature Tracks for High-Level Video Feature Extraction", Lecture Notes in Electrical Engineering, vol. 158: Analysis, Retrieval and Delivery of Multimedia Content, N. Adami, A. Cavallaro, R. Leonardi, P. Migliorati (Editors), ISBN 978-1-4614-3830-4, Springer, 2012.

Exploiting gaze movements for automatic video annotation

S. Vrochidis, I. Patras and I Kompatsiaris, "Exploiting gaze movements for automatic video annotation", in Proceedings of the 13th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2012), Dublin, Ireland, May 23-25, 2012.

CERTH-ITI is the best in interactive known-item video search!

CERTH-ITI participated to the Known-Item Search (KIS) Task of TRECVID 2011 with the interactive video retrieval engine VERGE. VERGE produced the best results, among the submissions made by all institutions participating to TRECVID 2011 KIS task (12 runs from 4 different institutions) with interactive systems. The latest version of VERGE supports advanced retrieval functionalities including visual similarity search, visual concept-based retrieval, user implicit feedback-based fusion, video similarity based on PLSA and full text search. More information about VERGE is available here. Feel free to try on line the latest version of VERGE and search in the TRECVID 2011 KIS test data collection.

System for video temporal segmentation to scenes

V. Mezaris, I. Kompatsiaris, "System for segmenting in time a video to scenes", Greek Industrial Property Organization (OBI), Patent No. GR1007303, Int. Cl. G06K 9/00, G06F 17/30 (valid until 23-04-2030).

Introduction to the Special issue on Image and Video Retrieval: Theory and Applications

Yiannis Kompatsiaris, Stephane Marchand-Maillet, Roelof van Zwol and S├ębastien Marcel, "Introduction to the Special issue on Image and Video Retrieval: Theory and Applications", Multimedia Tools and Applications, vol. 55, no. 1, pp. 1-6, October 2011.

A system for the semantic multi-modal analysis of news audio-visual content

A new journal publication, jointly authored by members of CERTH, DFKI and the University of Twente, was recently accepted for publication:

V. Mezaris, S. Gidaros, G. Th. Papadopoulos, W. Kasper, J. Steffen, R. Ordelman, M. Huijbregts, F. de Jong, I. Kompatsiaris, M. G. Strintzis, "A system for the semantic multi-modal analysis of news audio-visual content", EURASIP Journal on Advances in Signal Processing, accepted for publication, 2010.

A system for the semantic multi-modal analysis of news audio-visual content

V. Mezaris, S. Gidaros, G. Th. Papadopoulos, W. Kasper, J. Steffen, R. Ordelman, M. Huijbregts, F. de Jong, I. Kompatsiaris, M. G. Strintzis, "A system for the semantic multi-modal analysis of news audio-visual content", EURASIP Journal on Advances in Signal Processing, vol. 2010, 2010.

VIA

Video Image Annotation Tool (VIA) website launched. VIA is a image/video annotation tool by CERTH-ITI, The development of this tool has been supported by the Bootstrapping Ontology Evolution with Multimedia Information Extraction (BOEMIE)(FP6-027538) and aceMedia(FP6-001765) projects.
Syndicate content