IRISA at TrecVid2015: Leveraging Multimodal LDA for Video Hyperlinking

Abstract : This paper presents the runs that we submitted in the context of the TRECVid 2015 Video Hyperlinking task. The task aims at proposing a set of video segments, called targets, to complement a query video segment defined as anchor. We used automatic transcripts and automatically extracted visual concept as input data. Two out of four runs use cross-modal LDA as a means to jointly make use of visual and audio information in the videos. As a contrast, one is based solely on visual information, and a combination of the cross-modal and visual runs is considered. After presenting the approaches, we discuss the performance obtained by the respective runs, as well as some of the limitations of the evaluation process.
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01403726
Contributor : Pascale Sébillot <>
Submitted on : Sunday, November 27, 2016 - 2:11:49 PM
Last modification on : Thursday, February 7, 2019 - 4:13:45 PM
Document(s) archivé(s) le : Tuesday, March 21, 2017 - 10:06:22 AM

File

TRECVid_Workshop_paper_final.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01403726, version 1

Citation

Anca-Roxana Simon, Ronan Sicre, Rémi Bois, Guillaume Gravier, Pascale Sébillot. IRISA at TrecVid2015: Leveraging Multimodal LDA for Video Hyperlinking. TRECVid 2015 Workshop, Nov 2015, Gaithersburg, United States. ⟨hal-01403726⟩

Share

Metrics

Record views

1486

Files downloads

77