Ecole d'ingénieur et centre de recherche en Sciences du numérique

Automatic fine-grained hyperlinking of videos within a closed collection using scene segmentation

Apostolidis, Evlampios; Mezaris, Vasileios; Sahuguet, Mathilde; Huet, Benoit; Cervenková, Barbora; Stein, Daniel; Eickeler, Stefan; Redondo Garcia, José Luis; Troncy, Raphaël; Pikora, Lukas

ACMMM 2014, 22nd ACM International Conference on Multimedia, November 3-7, 2014, Orlando, Florida, USA

This paper introduces a framework for establishing links between related media fragments within a collection of videos. A set of analysis techniques is applied for extracting information from di erent types of data. Visual-based shot and scene segmentation is performed for de ning media fragments at di erent granularity levels, while visual cues are detected from keyframes of the video via concept detection and optical character recognition (OCR). Keyword extraction is applied on textual data such as the output of OCR, subtitles and metadata. This set of results is used for the automatic identi cation and linking of related media fragments. The proposed framework exhibited competitive performance in the Video Hyperlinking sub-task of MediaEval 2013, indicating that video scene segmentation can provide more meaningful segments, compared to other decomposition methods, for hyperlinking purposes.

Document Doi Bibtex

Titre:Automatic fine-grained hyperlinking of videos within a closed collection using scene segmentation
Mots Clés:Video hyperlinking; scene segmentation; con- cept detection; keyword extraction; data indexing
Type:Conférence
Langue:English
Ville:Orlando
Pays:ÉTATS-UNIS
Date:
Département:Data Science
Eurecom ref:4398
Copyright: © ACM, 2014. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACMMM 2014, 22nd ACM International Conference on Multimedia, November 3-7, 2014, Orlando, Florida, USA http://dx.doi.org/10.1145/2647868.2655041
Bibtex: @inproceedings{EURECOM+4398, doi = {http://dx.doi.org/10.1145/2647868.2655041}, year = {2014}, title = {{A}utomatic fine-grained hyperlinking of videos within a closed collection using scene segmentation}, author = {{A}postolidis, {E}vlampios and {M}ezaris, {V}asileios and {S}ahuguet, {M}athilde and {H}uet, {B}enoit and {C}ervenkov{\'a}, {B}arbora and {S}tein, {D}aniel and {E}ickeler, {S}tefan and {R}edondo {G}arcia, {J}os{\'e} {L}uis and {T}roncy, {R}apha{\"e}l and {P}ikora, {L}ukas}, booktitle = {{ACMMM} 2014, 22nd {ACM} {I}nternational {C}onference on {M}ultimedia, {N}ovember 3-7, 2014, {O}rlando, {F}lorida, {USA}}, address = {{O}rlando, {\'{E}}{TATS}-{UNIS}}, month = {11}, url = {http://www.eurecom.fr/publication/4398} }
Voir aussi: