Approach for Video Classification with Multi-label on YouTube-8M Dataset

Video traffic is increasing at a considerable rate due to the spread of personal media and advancements in media technology. Accordingly, there is a growing need for techniques to automatically classify moving images. This paper use NetVLAD and NetFV models and the Huber loss function for video clas...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-08
Main Authors: Shin, Kwangsoo, Jeon, Junhyeong, Lee, Seungbin, Lim, Boyoung, Jeong, Minsoo, Nang, Jongho
Format: Article
Language:English
Subjects:
Datasets
Image classification
Information dissemination
Moving images
Video data
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Shin, Kwangsoo
Jeon, Junhyeong
Lee, Seungbin
Lim, Boyoung
Jeong, Minsoo
Nang, Jongho
description Video traffic is increasing at a considerable rate due to the spread of personal media and advancements in media technology. Accordingly, there is a growing need for techniques to automatically classify moving images. This paper use NetVLAD and NetFV models and the Huber loss function for video classification problem and YouTube-8M dataset to verify the experiment. We tried various attempts according to the dataset and optimize hyperparameters, ultimately obtain a GAP score of 0.8668.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2095186940</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2095186940</sourcerecordid><originalsourceid>FETCH-proquest_journals_20951869403</originalsourceid><addsrcrecordid>eNqNjEELgjAYhkcQJOV_-KDzYG5qegwrvHiToJN86sTJcOY2-vt56Ad0euF5Ht4dCbgQEc1izg8ktHZijPH0wpNEBKS8LstqsBthMCs8VS8NFBqtVYPq0Ckzw0e5ESqvnaIaW6lhYy_ja99KmlVwQ4dWuhPZD6itDH97JOfHvS5Kut2_vbSumYxf5001nOVJlKV5zMR_1Rf1EjtT</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2095186940</pqid></control><display><type>article</type><title>Approach for Video Classification with Multi-label on YouTube-8M Dataset</title><source>Publicly Available Content Database</source><creator>Shin, Kwangsoo ; Jeon, Junhyeong ; Lee, Seungbin ; Lim, Boyoung ; Jeong, Minsoo ; Nang, Jongho</creator><creatorcontrib>Shin, Kwangsoo ; Jeon, Junhyeong ; Lee, Seungbin ; Lim, Boyoung ; Jeong, Minsoo ; Nang, Jongho</creatorcontrib><description>Video traffic is increasing at a considerable rate due to the spread of personal media and advancements in media technology. Accordingly, there is a growing need for techniques to automatically classify moving images. This paper use NetVLAD and NetFV models and the Huber loss function for video classification problem and YouTube-8M dataset to verify the experiment. We tried various attempts according to the dataset and optimize hyperparameters, ultimately obtain a GAP score of 0.8668.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Datasets ; Image classification ; Information dissemination ; Moving images ; Video data</subject><ispartof>arXiv.org, 2018-08</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2095186940?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Shin, Kwangsoo</creatorcontrib><creatorcontrib>Jeon, Junhyeong</creatorcontrib><creatorcontrib>Lee, Seungbin</creatorcontrib><creatorcontrib>Lim, Boyoung</creatorcontrib><creatorcontrib>Jeong, Minsoo</creatorcontrib><creatorcontrib>Nang, Jongho</creatorcontrib><title>Approach for Video Classification with Multi-label on YouTube-8M Dataset</title><title>arXiv.org</title><description>Video traffic is increasing at a considerable rate due to the spread of personal media and advancements in media technology. Accordingly, there is a growing need for techniques to automatically classify moving images. This paper use NetVLAD and NetFV models and the Huber loss function for video classification problem and YouTube-8M dataset to verify the experiment. We tried various attempts according to the dataset and optimize hyperparameters, ultimately obtain a GAP score of 0.8668.</description><subject>Datasets</subject><subject>Image classification</subject><subject>Information dissemination</subject><subject>Moving images</subject><subject>Video data</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjEELgjAYhkcQJOV_-KDzYG5qegwrvHiToJN86sTJcOY2-vt56Ad0euF5Ht4dCbgQEc1izg8ktHZijPH0wpNEBKS8LstqsBthMCs8VS8NFBqtVYPq0Ckzw0e5ESqvnaIaW6lhYy_ja99KmlVwQ4dWuhPZD6itDH97JOfHvS5Kut2_vbSumYxf5001nOVJlKV5zMR_1Rf1EjtT</recordid><startdate>20180830</startdate><enddate>20180830</enddate><creator>Shin, Kwangsoo</creator><creator>Jeon, Junhyeong</creator><creator>Lee, Seungbin</creator><creator>Lim, Boyoung</creator><creator>Jeong, Minsoo</creator><creator>Nang, Jongho</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20180830</creationdate><title>Approach for Video Classification with Multi-label on YouTube-8M Dataset</title><author>Shin, Kwangsoo ; Jeon, Junhyeong ; Lee, Seungbin ; Lim, Boyoung ; Jeong, Minsoo ; Nang, Jongho</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20951869403</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Datasets</topic><topic>Image classification</topic><topic>Information dissemination</topic><topic>Moving images</topic><topic>Video data</topic><toplevel>online_resources</toplevel><creatorcontrib>Shin, Kwangsoo</creatorcontrib><creatorcontrib>Jeon, Junhyeong</creatorcontrib><creatorcontrib>Lee, Seungbin</creatorcontrib><creatorcontrib>Lim, Boyoung</creatorcontrib><creatorcontrib>Jeong, Minsoo</creatorcontrib><creatorcontrib>Nang, Jongho</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shin, Kwangsoo</au><au>Jeon, Junhyeong</au><au>Lee, Seungbin</au><au>Lim, Boyoung</au><au>Jeong, Minsoo</au><au>Nang, Jongho</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Approach for Video Classification with Multi-label on YouTube-8M Dataset</atitle><jtitle>arXiv.org</jtitle><date>2018-08-30</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Video traffic is increasing at a considerable rate due to the spread of personal media and advancements in media technology. Accordingly, there is a growing need for techniques to automatically classify moving images. This paper use NetVLAD and NetFV models and the Huber loss function for video classification problem and YouTube-8M dataset to verify the experiment. We tried various attempts according to the dataset and optimize hyperparameters, ultimately obtain a GAP score of 0.8668.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2095186940
source Publicly Available Content Database
subjects Datasets
Image classification
Information dissemination
Moving images
Video data
title Approach for Video Classification with Multi-label on YouTube-8M Dataset
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T17%3A51%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Approach%20for%20Video%20Classification%20with%20Multi-label%20on%20YouTube-8M%20Dataset&rft.jtitle=arXiv.org&rft.au=Shin,%20Kwangsoo&rft.date=2018-08-30&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2095186940%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20951869403%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2095186940&rft_id=info:pmid/&rfr_iscdi=true