1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
Video panoptic segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. We believe that the decoupling strategy proposed by DVIS enables more effective utilization of temporal information for both "thi...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| 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 | Zhang, Tao Tian, Xingye Wei, Haoran Wu, Yu Ji, Shunping Wang, Xuebo Tao, Xin Zhang, Yuan Wan, Pengfei |
| description | Video panoptic segmentation is a challenging task that serves as the
cornerstone of numerous downstream applications, including video editing and
autonomous driving. We believe that the decoupling strategy proposed by DVIS
enables more effective utilization of temporal information for both "thing" and
"stuff" objects. In this report, we successfully validated the effectiveness of
the decoupling strategy in video panoptic segmentation. Finally, our method
achieved a VPQ score of 51.4 and 53.7 in the development and test phases,
respectively, and ultimately ranked 1st in the VPS track of the 2nd PVUW
Challenge. The code is available at https://github.com/zhang-tao-whu/DVIS |
| doi_str_mv | 10.48550/arxiv.2306.04091 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2306_04091</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2306_04091</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-15a15be1eb5448b47b0fe0e534d189f85f079845eb650c4e5b287339c4c0da533</originalsourceid><addsrcrecordid>eNotz0FOwzAQhWFvWKDCAVjhCySMY0_isEMRFKRKRGopy2jsjEskN67SgOD2qIXVW_1P-oS4UZAbiwh3NH0PX3mhoczBQK0uxVIdZ9lG8izXKX7OQxplSJNst2_vsvmgGHncsSyg0PdyO_ScZEtjOsyDl2ve7Xmc6RRdiYtA8cjX_7sQm6fHTfOcrV6XL83DKqOyUplCUuhYsUNjrDOVg8DAqE2vbB0sBqhqa5BdieANoytspXXtjYeeUOuFuP27PUu6wzTsafrpTqLuLNK_8PlEHQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation</title><source>arXiv.org</source><creator>Zhang, Tao ; Tian, Xingye ; Wei, Haoran ; Wu, Yu ; Ji, Shunping ; Wang, Xuebo ; Tao, Xin ; Zhang, Yuan ; Wan, Pengfei</creator><creatorcontrib>Zhang, Tao ; Tian, Xingye ; Wei, Haoran ; Wu, Yu ; Ji, Shunping ; Wang, Xuebo ; Tao, Xin ; Zhang, Yuan ; Wan, Pengfei</creatorcontrib><description>Video panoptic segmentation is a challenging task that serves as the
cornerstone of numerous downstream applications, including video editing and
autonomous driving. We believe that the decoupling strategy proposed by DVIS
enables more effective utilization of temporal information for both "thing" and
"stuff" objects. In this report, we successfully validated the effectiveness of
the decoupling strategy in video panoptic segmentation. Finally, our method
achieved a VPQ score of 51.4 and 53.7 in the development and test phases,
respectively, and ultimately ranked 1st in the VPS track of the 2nd PVUW
Challenge. The code is available at https://github.com/zhang-tao-whu/DVIS</description><identifier>DOI: 10.48550/arxiv.2306.04091</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2023-06</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2306.04091$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2306.04091$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Tao</creatorcontrib><creatorcontrib>Tian, Xingye</creatorcontrib><creatorcontrib>Wei, Haoran</creatorcontrib><creatorcontrib>Wu, Yu</creatorcontrib><creatorcontrib>Ji, Shunping</creatorcontrib><creatorcontrib>Wang, Xuebo</creatorcontrib><creatorcontrib>Tao, Xin</creatorcontrib><creatorcontrib>Zhang, Yuan</creatorcontrib><creatorcontrib>Wan, Pengfei</creatorcontrib><title>1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation</title><description>Video panoptic segmentation is a challenging task that serves as the
cornerstone of numerous downstream applications, including video editing and
autonomous driving. We believe that the decoupling strategy proposed by DVIS
enables more effective utilization of temporal information for both "thing" and
"stuff" objects. In this report, we successfully validated the effectiveness of
the decoupling strategy in video panoptic segmentation. Finally, our method
achieved a VPQ score of 51.4 and 53.7 in the development and test phases,
respectively, and ultimately ranked 1st in the VPS track of the 2nd PVUW
Challenge. The code is available at https://github.com/zhang-tao-whu/DVIS</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz0FOwzAQhWFvWKDCAVjhCySMY0_isEMRFKRKRGopy2jsjEskN67SgOD2qIXVW_1P-oS4UZAbiwh3NH0PX3mhoczBQK0uxVIdZ9lG8izXKX7OQxplSJNst2_vsvmgGHncsSyg0PdyO_ScZEtjOsyDl2ve7Xmc6RRdiYtA8cjX_7sQm6fHTfOcrV6XL83DKqOyUplCUuhYsUNjrDOVg8DAqE2vbB0sBqhqa5BdieANoytspXXtjYeeUOuFuP27PUu6wzTsafrpTqLuLNK_8PlEHQ</recordid><startdate>20230606</startdate><enddate>20230606</enddate><creator>Zhang, Tao</creator><creator>Tian, Xingye</creator><creator>Wei, Haoran</creator><creator>Wu, Yu</creator><creator>Ji, Shunping</creator><creator>Wang, Xuebo</creator><creator>Tao, Xin</creator><creator>Zhang, Yuan</creator><creator>Wan, Pengfei</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230606</creationdate><title>1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation</title><author>Zhang, Tao ; Tian, Xingye ; Wei, Haoran ; Wu, Yu ; Ji, Shunping ; Wang, Xuebo ; Tao, Xin ; Zhang, Yuan ; Wan, Pengfei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-15a15be1eb5448b47b0fe0e534d189f85f079845eb650c4e5b287339c4c0da533</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Tao</creatorcontrib><creatorcontrib>Tian, Xingye</creatorcontrib><creatorcontrib>Wei, Haoran</creatorcontrib><creatorcontrib>Wu, Yu</creatorcontrib><creatorcontrib>Ji, Shunping</creatorcontrib><creatorcontrib>Wang, Xuebo</creatorcontrib><creatorcontrib>Tao, Xin</creatorcontrib><creatorcontrib>Zhang, Yuan</creatorcontrib><creatorcontrib>Wan, Pengfei</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Tao</au><au>Tian, Xingye</au><au>Wei, Haoran</au><au>Wu, Yu</au><au>Ji, Shunping</au><au>Wang, Xuebo</au><au>Tao, Xin</au><au>Zhang, Yuan</au><au>Wan, Pengfei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation</atitle><date>2023-06-06</date><risdate>2023</risdate><abstract>Video panoptic segmentation is a challenging task that serves as the
cornerstone of numerous downstream applications, including video editing and
autonomous driving. We believe that the decoupling strategy proposed by DVIS
enables more effective utilization of temporal information for both "thing" and
"stuff" objects. In this report, we successfully validated the effectiveness of
the decoupling strategy in video panoptic segmentation. Finally, our method
achieved a VPQ score of 51.4 and 53.7 in the development and test phases,
respectively, and ultimately ranked 1st in the VPS track of the 2nd PVUW
Challenge. The code is available at https://github.com/zhang-tao-whu/DVIS</abstract><doi>10.48550/arxiv.2306.04091</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2306.04091 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2306_04091 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition |
| title | 1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T23%3A04%3A32IST&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=1st%20Place%20Solution%20for%20PVUW%20Challenge%202023:%20Video%20Panoptic%20Segmentation&rft.au=Zhang,%20Tao&rft.date=2023-06-06&rft_id=info:doi/10.48550/arxiv.2306.04091&rft_dat=%3Carxiv_GOX%3E2306_04091%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 |