Accuracy and Performance Comparison of Video Action Recognition Approaches
Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and infere...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2020-08 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Hutchinson, Matthew Samsi, Siddharth Arcand, William Bestor, David Bergeron, Bill Byun, Chansup Houle, Micheal Hubbell, Matthew Jones, Micheal Kepner, Jeremy Kirby, Andrew Michaleas, Peter Milechin, Lauren Mullen, Julie Prout, Andrew Rosa, Antonio Reuther, Albert Yee, Charles Gadepally, Vijay |
| description | Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen off-the-shelf and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system. |
| doi_str_mv | 10.48550/arxiv.2008.09037 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2008_09037</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2435940455</sourcerecordid><originalsourceid>FETCH-LOGICAL-a525-513e26985190abe9c766e1124f112fe140375b03b27fe28a27aabfbe0ac599273</originalsourceid><addsrcrecordid>eNotj01Lw0AQhhdBsNT-AE8GPKfOzu4m2WMofiIoUryGyXZWU2w2blqx_9619TIzL7wMzyPEhYS5royBa4o_3fccAao5WFDliZigUjKvNOKZmI3jGgCwKNEYNRGPtXO7SG6fUb_KXjj6EDfUO84WYTNQ7MbQZ8Fnb92KQ1a7bZfyK7vw3neHux6GGMh98HguTj19jjz731OxvL1ZLu7zp-e7h0X9lJNBkxupGAtbGWmBWrauLAqWErVPw7PUCdm0oFosPWNFWBK1vmUgZ6zFUk3F5fHtQbQZYrehuG_-hJuDcGpcHRuJ7GvH47ZZh13sE1ODWhmrQSf3X5JnV9s</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2435940455</pqid></control><display><type>article</type><title>Accuracy and Performance Comparison of Video Action Recognition Approaches</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Hutchinson, Matthew ; Samsi, Siddharth ; Arcand, William ; Bestor, David ; Bergeron, Bill ; Byun, Chansup ; Houle, Micheal ; Hubbell, Matthew ; Jones, Micheal ; Kepner, Jeremy ; Kirby, Andrew ; Michaleas, Peter ; Milechin, Lauren ; Mullen, Julie ; Prout, Andrew ; Rosa, Antonio ; Reuther, Albert ; Yee, Charles ; Gadepally, Vijay</creator><creatorcontrib>Hutchinson, Matthew ; Samsi, Siddharth ; Arcand, William ; Bestor, David ; Bergeron, Bill ; Byun, Chansup ; Houle, Micheal ; Hubbell, Matthew ; Jones, Micheal ; Kepner, Jeremy ; Kirby, Andrew ; Michaleas, Peter ; Milechin, Lauren ; Mullen, Julie ; Prout, Andrew ; Rosa, Antonio ; Reuther, Albert ; Yee, Charles ; Gadepally, Vijay</creatorcontrib><description>Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen off-the-shelf and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2008.09037</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Accuracy ; Algorithms ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Computer Science - Performance ; Model accuracy ; Recognition ; Training</subject><ispartof>arXiv.org, 2020-08</ispartof><rights>2020. 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><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2008.09037$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1109/HPEC43674.2020.9286249$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Hutchinson, Matthew</creatorcontrib><creatorcontrib>Samsi, Siddharth</creatorcontrib><creatorcontrib>Arcand, William</creatorcontrib><creatorcontrib>Bestor, David</creatorcontrib><creatorcontrib>Bergeron, Bill</creatorcontrib><creatorcontrib>Byun, Chansup</creatorcontrib><creatorcontrib>Houle, Micheal</creatorcontrib><creatorcontrib>Hubbell, Matthew</creatorcontrib><creatorcontrib>Jones, Micheal</creatorcontrib><creatorcontrib>Kepner, Jeremy</creatorcontrib><creatorcontrib>Kirby, Andrew</creatorcontrib><creatorcontrib>Michaleas, Peter</creatorcontrib><creatorcontrib>Milechin, Lauren</creatorcontrib><creatorcontrib>Mullen, Julie</creatorcontrib><creatorcontrib>Prout, Andrew</creatorcontrib><creatorcontrib>Rosa, Antonio</creatorcontrib><creatorcontrib>Reuther, Albert</creatorcontrib><creatorcontrib>Yee, Charles</creatorcontrib><creatorcontrib>Gadepally, Vijay</creatorcontrib><title>Accuracy and Performance Comparison of Video Action Recognition Approaches</title><title>arXiv.org</title><description>Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen off-the-shelf and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Performance</subject><subject>Model accuracy</subject><subject>Recognition</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj01Lw0AQhhdBsNT-AE8GPKfOzu4m2WMofiIoUryGyXZWU2w2blqx_9619TIzL7wMzyPEhYS5royBa4o_3fccAao5WFDliZigUjKvNOKZmI3jGgCwKNEYNRGPtXO7SG6fUb_KXjj6EDfUO84WYTNQ7MbQZ8Fnb92KQ1a7bZfyK7vw3neHux6GGMh98HguTj19jjz731OxvL1ZLu7zp-e7h0X9lJNBkxupGAtbGWmBWrauLAqWErVPw7PUCdm0oFosPWNFWBK1vmUgZ6zFUk3F5fHtQbQZYrehuG_-hJuDcGpcHRuJ7GvH47ZZh13sE1ODWhmrQSf3X5JnV9s</recordid><startdate>20200820</startdate><enddate>20200820</enddate><creator>Hutchinson, Matthew</creator><creator>Samsi, Siddharth</creator><creator>Arcand, William</creator><creator>Bestor, David</creator><creator>Bergeron, Bill</creator><creator>Byun, Chansup</creator><creator>Houle, Micheal</creator><creator>Hubbell, Matthew</creator><creator>Jones, Micheal</creator><creator>Kepner, Jeremy</creator><creator>Kirby, Andrew</creator><creator>Michaleas, Peter</creator><creator>Milechin, Lauren</creator><creator>Mullen, Julie</creator><creator>Prout, Andrew</creator><creator>Rosa, Antonio</creator><creator>Reuther, Albert</creator><creator>Yee, Charles</creator><creator>Gadepally, Vijay</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><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200820</creationdate><title>Accuracy and Performance Comparison of Video Action Recognition Approaches</title><author>Hutchinson, Matthew ; Samsi, Siddharth ; Arcand, William ; Bestor, David ; Bergeron, Bill ; Byun, Chansup ; Houle, Micheal ; Hubbell, Matthew ; Jones, Micheal ; Kepner, Jeremy ; Kirby, Andrew ; Michaleas, Peter ; Milechin, Lauren ; Mullen, Julie ; Prout, Andrew ; Rosa, Antonio ; Reuther, Albert ; Yee, Charles ; Gadepally, Vijay</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a525-513e26985190abe9c766e1124f112fe140375b03b27fe28a27aabfbe0ac599273</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Performance</topic><topic>Model accuracy</topic><topic>Recognition</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Hutchinson, Matthew</creatorcontrib><creatorcontrib>Samsi, Siddharth</creatorcontrib><creatorcontrib>Arcand, William</creatorcontrib><creatorcontrib>Bestor, David</creatorcontrib><creatorcontrib>Bergeron, Bill</creatorcontrib><creatorcontrib>Byun, Chansup</creatorcontrib><creatorcontrib>Houle, Micheal</creatorcontrib><creatorcontrib>Hubbell, Matthew</creatorcontrib><creatorcontrib>Jones, Micheal</creatorcontrib><creatorcontrib>Kepner, Jeremy</creatorcontrib><creatorcontrib>Kirby, Andrew</creatorcontrib><creatorcontrib>Michaleas, Peter</creatorcontrib><creatorcontrib>Milechin, Lauren</creatorcontrib><creatorcontrib>Mullen, Julie</creatorcontrib><creatorcontrib>Prout, Andrew</creatorcontrib><creatorcontrib>Rosa, Antonio</creatorcontrib><creatorcontrib>Reuther, Albert</creatorcontrib><creatorcontrib>Yee, Charles</creatorcontrib><creatorcontrib>Gadepally, Vijay</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</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><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hutchinson, Matthew</au><au>Samsi, Siddharth</au><au>Arcand, William</au><au>Bestor, David</au><au>Bergeron, Bill</au><au>Byun, Chansup</au><au>Houle, Micheal</au><au>Hubbell, Matthew</au><au>Jones, Micheal</au><au>Kepner, Jeremy</au><au>Kirby, Andrew</au><au>Michaleas, Peter</au><au>Milechin, Lauren</au><au>Mullen, Julie</au><au>Prout, Andrew</au><au>Rosa, Antonio</au><au>Reuther, Albert</au><au>Yee, Charles</au><au>Gadepally, Vijay</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accuracy and Performance Comparison of Video Action Recognition Approaches</atitle><jtitle>arXiv.org</jtitle><date>2020-08-20</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen off-the-shelf and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2008.09037</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2020-08 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2008_09037 |
| source | arXiv.org; Free E- Journals |
| subjects | Accuracy Algorithms Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Computer Science - Performance Model accuracy Recognition Training |
| title | Accuracy and Performance Comparison of Video Action Recognition Approaches |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T11%3A58%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accuracy%20and%20Performance%20Comparison%20of%20Video%20Action%20Recognition%20Approaches&rft.jtitle=arXiv.org&rft.au=Hutchinson,%20Matthew&rft.date=2020-08-20&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2008.09037&rft_dat=%3Cproquest_arxiv%3E2435940455%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2435940455&rft_id=info:pmid/&rfr_iscdi=true |