Large-scale Video Classification guided by Batch Normalized LSTM Translator
Youtube-8M dataset enhances the development of large-scale video recognition technology as ImageNet dataset has encouraged image classification, recognition and detection of artificial intelligence fields. For this large video dataset, it is a challenging task to classify a huge amount of multi-labe...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Yoo, Jae Hyeon |
| description | Youtube-8M dataset enhances the development of large-scale video recognition
technology as ImageNet dataset has encouraged image classification, recognition
and detection of artificial intelligence fields. For this large video dataset,
it is a challenging task to classify a huge amount of multi-labels. By change
of perspective, we propose a novel method by regarding labels as words. In
details, we describe online learning approaches to multi-label video
classification that are guided by deep recurrent neural networks for video to
sentence translator. We designed the translator based on LSTMs and found out
that a stochastic gating before the input of each LSTM cell can help us to
design the structural details. In addition, we adopted batch normalizations
into our models to improve our LSTM models. Since our models are feature
extractors, they can be used with other classifiers. Finally we report improved
validation results of our models on large-scale Youtube-8M datasets and
discussions for the further improvement. |
| doi_str_mv | 10.48550/arxiv.1707.04045 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1707_04045</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1707_04045</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-b25cabdcdec072811b0fdbb75638bd1ef9962913c89e03da6ab42c48e6fe952f3</originalsourceid><addsrcrecordid>eNotz7tOwzAYhmEvDKhwAUz4BhJsx8cRIk4iwEDEGv0-FUtug-yAKFdPKUyf9A6f9CB0RknLtRDkAspX-mypIqolnHBxjB4GKOvQVAc54Nfkw4z7DLWmmBwsad7i9ce-emx3-AoW94af5rKBnL73bXgZH_FYYFszLHM5QUcRcg2n_7tC48312N81w_PtfX85NCCVaCwTDqx3PjiimKbUkuitVUJ22noaojGSGdo5bQLpPEiwnDmug4zBCBa7FTr_uz1opveSNlB2069qOqi6H4-5SDA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Large-scale Video Classification guided by Batch Normalized LSTM Translator</title><source>arXiv.org</source><creator>Yoo, Jae Hyeon</creator><creatorcontrib>Yoo, Jae Hyeon</creatorcontrib><description>Youtube-8M dataset enhances the development of large-scale video recognition
technology as ImageNet dataset has encouraged image classification, recognition
and detection of artificial intelligence fields. For this large video dataset,
it is a challenging task to classify a huge amount of multi-labels. By change
of perspective, we propose a novel method by regarding labels as words. In
details, we describe online learning approaches to multi-label video
classification that are guided by deep recurrent neural networks for video to
sentence translator. We designed the translator based on LSTMs and found out
that a stochastic gating before the input of each LSTM cell can help us to
design the structural details. In addition, we adopted batch normalizations
into our models to improve our LSTM models. Since our models are feature
extractors, they can be used with other classifiers. Finally we report improved
validation results of our models on large-scale Youtube-8M datasets and
discussions for the further improvement.</description><identifier>DOI: 10.48550/arxiv.1707.04045</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2017-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1707.04045$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1707.04045$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Yoo, Jae Hyeon</creatorcontrib><title>Large-scale Video Classification guided by Batch Normalized LSTM Translator</title><description>Youtube-8M dataset enhances the development of large-scale video recognition
technology as ImageNet dataset has encouraged image classification, recognition
and detection of artificial intelligence fields. For this large video dataset,
it is a challenging task to classify a huge amount of multi-labels. By change
of perspective, we propose a novel method by regarding labels as words. In
details, we describe online learning approaches to multi-label video
classification that are guided by deep recurrent neural networks for video to
sentence translator. We designed the translator based on LSTMs and found out
that a stochastic gating before the input of each LSTM cell can help us to
design the structural details. In addition, we adopted batch normalizations
into our models to improve our LSTM models. Since our models are feature
extractors, they can be used with other classifiers. Finally we report improved
validation results of our models on large-scale Youtube-8M datasets and
discussions for the further improvement.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7tOwzAYhmEvDKhwAUz4BhJsx8cRIk4iwEDEGv0-FUtug-yAKFdPKUyf9A6f9CB0RknLtRDkAspX-mypIqolnHBxjB4GKOvQVAc54Nfkw4z7DLWmmBwsad7i9ce-emx3-AoW94af5rKBnL73bXgZH_FYYFszLHM5QUcRcg2n_7tC48312N81w_PtfX85NCCVaCwTDqx3PjiimKbUkuitVUJ22noaojGSGdo5bQLpPEiwnDmug4zBCBa7FTr_uz1opveSNlB2069qOqi6H4-5SDA</recordid><startdate>20170713</startdate><enddate>20170713</enddate><creator>Yoo, Jae Hyeon</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20170713</creationdate><title>Large-scale Video Classification guided by Batch Normalized LSTM Translator</title><author>Yoo, Jae Hyeon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-b25cabdcdec072811b0fdbb75638bd1ef9962913c89e03da6ab42c48e6fe952f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Yoo, Jae Hyeon</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yoo, Jae Hyeon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Large-scale Video Classification guided by Batch Normalized LSTM Translator</atitle><date>2017-07-13</date><risdate>2017</risdate><abstract>Youtube-8M dataset enhances the development of large-scale video recognition
technology as ImageNet dataset has encouraged image classification, recognition
and detection of artificial intelligence fields. For this large video dataset,
it is a challenging task to classify a huge amount of multi-labels. By change
of perspective, we propose a novel method by regarding labels as words. In
details, we describe online learning approaches to multi-label video
classification that are guided by deep recurrent neural networks for video to
sentence translator. We designed the translator based on LSTMs and found out
that a stochastic gating before the input of each LSTM cell can help us to
design the structural details. In addition, we adopted batch normalizations
into our models to improve our LSTM models. Since our models are feature
extractors, they can be used with other classifiers. Finally we report improved
validation results of our models on large-scale Youtube-8M datasets and
discussions for the further improvement.</abstract><doi>10.48550/arxiv.1707.04045</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1707.04045 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1707_04045 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition |
| title | Large-scale Video Classification guided by Batch Normalized LSTM Translator |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T13%3A40%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Large-scale%20Video%20Classification%20guided%20by%20Batch%20Normalized%20LSTM%20Translator&rft.au=Yoo,%20Jae%20Hyeon&rft.date=2017-07-13&rft_id=info:doi/10.48550/arxiv.1707.04045&rft_dat=%3Carxiv_GOX%3E1707_04045%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |