Loading…
Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection
Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Citations: | Items that cite this one |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c258t-52fbf3b854c9476c963a2dd0f45c43440c8a50e0cfa457cbadf101f54f848d473 |
|---|---|
| cites | |
| container_end_page | 2160 |
| container_issue | |
| container_start_page | 2153 |
| container_title | |
| container_volume | |
| creator | Barekatain, Mohammadamin Marti, Miquel Hsueh-Fu Shih Murray, Samuel Nakayama, Kotaro Matsuo, Yutaka Prendinger, Helmut |
| description | Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications. |
| doi_str_mv | 10.1109/CVPRW.2017.267 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8015001</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8015001</ieee_id><sourcerecordid>8015001</sourcerecordid><originalsourceid>FETCH-LOGICAL-c258t-52fbf3b854c9476c963a2dd0f45c43440c8a50e0cfa457cbadf101f54f848d473</originalsourceid><addsrcrecordid>eNotj01Lw0AYhFdBsNZevXjZP5D67vfGW0jVCoVK0Xosbza7EG0S2WwQ_72hepmZwzMDQ8gNgyVjkN-V-5fd-5IDM0uuzRm5YkpYDUYIfU5mnGnIjGL6kiyG4QMAGFilcjEju-3nmLDFrHCp6bt7WnS08LHBI903_nuS2vd0hQkHn2joIy37zo0x-i7R9djihJ-adOWTP6VrchHwOPjFv8_J2-PDa7nONtun57LYZI4rmzLFQxVEZZV0uTTa5Vogr2sIUjkppARnUYEHF1Aq4yqsAwMWlAxW2loaMSe3f7uN9_7wFZsW48_BAlPTP_EL561OtQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection</title><source>IEEE Xplore All Conference Series</source><creator>Barekatain, Mohammadamin ; Marti, Miquel ; Hsueh-Fu Shih ; Murray, Samuel ; Nakayama, Kotaro ; Matsuo, Yutaka ; Prendinger, Helmut</creator><creatorcontrib>Barekatain, Mohammadamin ; Marti, Miquel ; Hsueh-Fu Shih ; Murray, Samuel ; Nakayama, Kotaro ; Matsuo, Yutaka ; Prendinger, Helmut</creatorcontrib><description>Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.</description><identifier>EISSN: 2160-7516</identifier><identifier>EISBN: 1538607336</identifier><identifier>EISBN: 9781538607336</identifier><identifier>DOI: 10.1109/CVPRW.2017.267</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Conferences ; Data collection ; Mobile communication ; Surveillance ; Training ; Video sequences</subject><ispartof>2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, p.2153-2160</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c258t-52fbf3b854c9476c963a2dd0f45c43440c8a50e0cfa457cbadf101f54f848d473</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8015001$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8015001$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Barekatain, Mohammadamin</creatorcontrib><creatorcontrib>Marti, Miquel</creatorcontrib><creatorcontrib>Hsueh-Fu Shih</creatorcontrib><creatorcontrib>Murray, Samuel</creatorcontrib><creatorcontrib>Nakayama, Kotaro</creatorcontrib><creatorcontrib>Matsuo, Yutaka</creatorcontrib><creatorcontrib>Prendinger, Helmut</creatorcontrib><title>Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection</title><title>2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</title><addtitle>CVPRW</addtitle><description>Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.</description><subject>Cameras</subject><subject>Conferences</subject><subject>Data collection</subject><subject>Mobile communication</subject><subject>Surveillance</subject><subject>Training</subject><subject>Video sequences</subject><issn>2160-7516</issn><isbn>1538607336</isbn><isbn>9781538607336</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2017</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj01Lw0AYhFdBsNZevXjZP5D67vfGW0jVCoVK0Xosbza7EG0S2WwQ_72hepmZwzMDQ8gNgyVjkN-V-5fd-5IDM0uuzRm5YkpYDUYIfU5mnGnIjGL6kiyG4QMAGFilcjEju-3nmLDFrHCp6bt7WnS08LHBI903_nuS2vd0hQkHn2joIy37zo0x-i7R9djihJ-adOWTP6VrchHwOPjFv8_J2-PDa7nONtun57LYZI4rmzLFQxVEZZV0uTTa5Vogr2sIUjkppARnUYEHF1Aq4yqsAwMWlAxW2loaMSe3f7uN9_7wFZsW48_BAlPTP_EL561OtQ</recordid><startdate>201707</startdate><enddate>201707</enddate><creator>Barekatain, Mohammadamin</creator><creator>Marti, Miquel</creator><creator>Hsueh-Fu Shih</creator><creator>Murray, Samuel</creator><creator>Nakayama, Kotaro</creator><creator>Matsuo, Yutaka</creator><creator>Prendinger, Helmut</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201707</creationdate><title>Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection</title><author>Barekatain, Mohammadamin ; Marti, Miquel ; Hsueh-Fu Shih ; Murray, Samuel ; Nakayama, Kotaro ; Matsuo, Yutaka ; Prendinger, Helmut</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c258t-52fbf3b854c9476c963a2dd0f45c43440c8a50e0cfa457cbadf101f54f848d473</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Cameras</topic><topic>Conferences</topic><topic>Data collection</topic><topic>Mobile communication</topic><topic>Surveillance</topic><topic>Training</topic><topic>Video sequences</topic><toplevel>online_resources</toplevel><creatorcontrib>Barekatain, Mohammadamin</creatorcontrib><creatorcontrib>Marti, Miquel</creatorcontrib><creatorcontrib>Hsueh-Fu Shih</creatorcontrib><creatorcontrib>Murray, Samuel</creatorcontrib><creatorcontrib>Nakayama, Kotaro</creatorcontrib><creatorcontrib>Matsuo, Yutaka</creatorcontrib><creatorcontrib>Prendinger, Helmut</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Barekatain, Mohammadamin</au><au>Marti, Miquel</au><au>Hsueh-Fu Shih</au><au>Murray, Samuel</au><au>Nakayama, Kotaro</au><au>Matsuo, Yutaka</au><au>Prendinger, Helmut</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection</atitle><btitle>2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</btitle><stitle>CVPRW</stitle><date>2017-07</date><risdate>2017</risdate><spage>2153</spage><epage>2160</epage><pages>2153-2160</pages><eissn>2160-7516</eissn><eisbn>1538607336</eisbn><eisbn>9781538607336</eisbn><coden>IEEPAD</coden><abstract>Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.</abstract><pub>IEEE</pub><doi>10.1109/CVPRW.2017.267</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2160-7516 |
| ispartof | 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, p.2153-2160 |
| issn | 2160-7516 |
| language | eng |
| recordid | cdi_ieee_primary_8015001 |
| source | IEEE Xplore All Conference Series |
| subjects | Cameras Conferences Data collection Mobile communication Surveillance Training Video sequences |
| title | Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T06%3A16%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Okutama-Action:%20An%20Aerial%20View%20Video%20Dataset%20for%20Concurrent%20Human%20Action%20Detection&rft.btitle=2017%20IEEE%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20(CVPRW)&rft.au=Barekatain,%20Mohammadamin&rft.date=2017-07&rft.spage=2153&rft.epage=2160&rft.pages=2153-2160&rft.eissn=2160-7516&rft.coden=IEEPAD&rft_id=info:doi/10.1109/CVPRW.2017.267&rft.eisbn=1538607336&rft.eisbn_list=9781538607336&rft_dat=%3Cieee_CHZPO%3E8015001%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c258t-52fbf3b854c9476c963a2dd0f45c43440c8a50e0cfa457cbadf101f54f848d473%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8015001&rfr_iscdi=true |