Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity
International audience Video hyperlinking is the process of creating links within a collection of videos to help navigation and information seeking. Starting from a given set of video segments, called anchors, a set of related segments, called targets, must be provided. In past years, a number of co...
Main Authors: | , , , , , , |
---|---|
Other Authors: | , , , , , , , , , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2017
|
Subjects: | |
Online Access: | https://hal.science/hal-01498130 https://hal.science/hal-01498130v2/document https://hal.science/hal-01498130v2/file/diversity.pdf https://doi.org/10.1007/978-3-319-51814-5_16 |
id |
ftunivrennes1hal:oai:HAL:hal-01498130v2 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Université de Rennes 1: Publications scientifiques (HAL) |
op_collection_id |
ftunivrennes1hal |
language |
English |
topic |
[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] |
spellingShingle |
[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] Bois, Rémi Vukotić, Vedran Simon, Anca-Roxana Sicre, Ronan Raymond, Christian Sébillot, Pascale Gravier, Guillaume Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity |
topic_facet |
[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] |
description |
International audience Video hyperlinking is the process of creating links within a collection of videos to help navigation and information seeking. Starting from a given set of video segments, called anchors, a set of related segments, called targets, must be provided. In past years, a number of content-based approaches have been proposed with good results obtained by searching for target segments that are very similar to the anchor in terms of content and information. Unfortunately, relevance has been obtained to the expense of diversity. In this paper, we study multimodal approaches and their ability to provide a set of diverse yet relevant targets. We compare two recently introduced cross-modal approaches, namely, deep auto-encoders and bimodal LDA, and experimentally show that both provide significantly more diverse targets than a state-of-the-art baseline. Bimodal autoencoders offer the best trade-off between relevance and diversity, with bimodal LDA exhibiting slightly more diverse targets at a lower precision. |
author2 |
Creating and exploiting explicit links between multimedia fragments (LinkMedia) Inria Rennes – Bretagne Atlantique Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6) Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) LABEX CominLabs Linking Media in Acceptable Hypergraphs Amsaleg, Laurent Guðmundsson, Gylfi Þór Gurrin, Cathal Satoh, Shin’ichi |
format |
Conference Object |
author |
Bois, Rémi Vukotić, Vedran Simon, Anca-Roxana Sicre, Ronan Raymond, Christian Sébillot, Pascale Gravier, Guillaume |
author_facet |
Bois, Rémi Vukotić, Vedran Simon, Anca-Roxana Sicre, Ronan Raymond, Christian Sébillot, Pascale Gravier, Guillaume |
author_sort |
Bois, Rémi |
title |
Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity |
title_short |
Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity |
title_full |
Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity |
title_fullStr |
Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity |
title_full_unstemmed |
Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity |
title_sort |
exploiting multimodality in video hyperlinking to improve target diversity |
publisher |
HAL CCSD |
publishDate |
2017 |
url |
https://hal.science/hal-01498130 https://hal.science/hal-01498130v2/document https://hal.science/hal-01498130v2/file/diversity.pdf https://doi.org/10.1007/978-3-319-51814-5_16 |
op_coverage |
Reykyavik, Iceland |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
MMM2017 - International Conference on Multimedia Modeling https://hal.science/hal-01498130 MMM2017 - International Conference on Multimedia Modeling, Jan 2017, Reykyavik, Iceland. ⟨10.1007/978-3-319-51814-5_16⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-51814-5_16 hal-01498130 https://hal.science/hal-01498130 https://hal.science/hal-01498130v2/document https://hal.science/hal-01498130v2/file/diversity.pdf doi:10.1007/978-3-319-51814-5_16 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1007/978-3-319-51814-5_16 |
container_start_page |
185 |
op_container_end_page |
197 |
_version_ |
1766040525835599872 |
spelling |
ftunivrennes1hal:oai:HAL:hal-01498130v2 2023-05-15T16:50:22+02:00 Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity Bois, Rémi Vukotić, Vedran Simon, Anca-Roxana Sicre, Ronan Raymond, Christian Sébillot, Pascale Gravier, Guillaume Creating and exploiting explicit links between multimedia fragments (LinkMedia) Inria Rennes – Bretagne Atlantique Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6) Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) LABEX CominLabs Linking Media in Acceptable Hypergraphs Amsaleg, Laurent Guðmundsson, Gylfi Þór Gurrin, Cathal Satoh, Shin’ichi Reykyavik, Iceland 2017-01-04 https://hal.science/hal-01498130 https://hal.science/hal-01498130v2/document https://hal.science/hal-01498130v2/file/diversity.pdf https://doi.org/10.1007/978-3-319-51814-5_16 en eng HAL CCSD Springer info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-51814-5_16 hal-01498130 https://hal.science/hal-01498130 https://hal.science/hal-01498130v2/document https://hal.science/hal-01498130v2/file/diversity.pdf doi:10.1007/978-3-319-51814-5_16 info:eu-repo/semantics/OpenAccess MMM2017 - International Conference on Multimedia Modeling https://hal.science/hal-01498130 MMM2017 - International Conference on Multimedia Modeling, Jan 2017, Reykyavik, Iceland. ⟨10.1007/978-3-319-51814-5_16⟩ [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] info:eu-repo/semantics/conferenceObject Conference papers 2017 ftunivrennes1hal https://doi.org/10.1007/978-3-319-51814-5_16 2023-03-22T00:10:03Z International audience Video hyperlinking is the process of creating links within a collection of videos to help navigation and information seeking. Starting from a given set of video segments, called anchors, a set of related segments, called targets, must be provided. In past years, a number of content-based approaches have been proposed with good results obtained by searching for target segments that are very similar to the anchor in terms of content and information. Unfortunately, relevance has been obtained to the expense of diversity. In this paper, we study multimodal approaches and their ability to provide a set of diverse yet relevant targets. We compare two recently introduced cross-modal approaches, namely, deep auto-encoders and bimodal LDA, and experimentally show that both provide significantly more diverse targets than a state-of-the-art baseline. Bimodal autoencoders offer the best trade-off between relevance and diversity, with bimodal LDA exhibiting slightly more diverse targets at a lower precision. Conference Object Iceland Université de Rennes 1: Publications scientifiques (HAL) 185 197 |