{"id":"https://openalex.org/W3092718160","doi":"https://doi.org/10.1145/3394171.3413942","title":"Dual Temporal Memory Network for Efficient Video Object Segmentation","display_name":"Dual Temporal Memory Network for Efficient Video Object Segmentation","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092718160","doi":"https://doi.org/10.1145/3394171.3413942","mag":"3092718160"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413942","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075412755","display_name":"Kaihua Zhang","orcid":"https://orcid.org/0000-0002-1613-3401"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaihua Zhang","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447540","display_name":"Long Wang","orcid":"https://orcid.org/0000-0001-6695-6054"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Wang","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407381","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0001-9100-2906"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Netflix Inc., Los Gatos, CA, USA"],"affiliations":[{"raw_affiliation_string":"Netflix Inc., Los Gatos, CA, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115587783","display_name":"\u0411\u043e \u041b\u044e","orcid":"https://orcid.org/0000-0003-3045-628X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["JD Finance America Corporation, Mountain View, CA, CA, USA"],"affiliations":[{"raw_affiliation_string":"JD Finance America Corporation, Mountain View, CA, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404959","display_name":"Qingshan Liu","orcid":"https://orcid.org/0000-0002-5512-6984"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingshan Liu","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380625","display_name":"Zhu Li","orcid":"https://orcid.org/0000-0002-8246-177X"},"institutions":[{"id":"https://openalex.org/I75421653","display_name":"University of Missouri\u2013Kansas City","ror":"https://ror.org/01w0d5g70","country_code":"US","type":"education","lineage":["https://openalex.org/I75421653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu Li","raw_affiliation_strings":["University of Missouri, Kansas City, MO, USA"],"affiliations":[{"raw_affiliation_string":"University of Missouri, Kansas City, MO, USA","institution_ids":["https://openalex.org/I75421653"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075412755"],"corresponding_institution_ids":["https://openalex.org/I200845125"],"apc_list":null,"apc_paid":null,"fwci":1.6609,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86516099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1515","last_page":"1523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8335431814193726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6457757353782654},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6267646551132202},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5691881775856018},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5494382977485657},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47557488083839417},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.41172170639038086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335431814193726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6457757353782654},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6267646551132202},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5691881775856018},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5494382977485657},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47557488083839417},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.41172170639038086},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413942","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2102354443","https://openalex.org/W2109255472","https://openalex.org/W2110485445","https://openalex.org/W2113708607","https://openalex.org/W2144499799","https://openalex.org/W2157331557","https://openalex.org/W2162813810","https://openalex.org/W2187051054","https://openalex.org/W2194775991","https://openalex.org/W2462481369","https://openalex.org/W2470139095","https://openalex.org/W2552531400","https://openalex.org/W2562457735","https://openalex.org/W2564998703","https://openalex.org/W2610147486","https://openalex.org/W2724418412","https://openalex.org/W2734938207","https://openalex.org/W2749835604","https://openalex.org/W2784814091","https://openalex.org/W2794847483","https://openalex.org/W2799157347","https://openalex.org/W2799239273","https://openalex.org/W2890853604","https://openalex.org/W2948729509","https://openalex.org/W2950424701","https://openalex.org/W2962825871","https://openalex.org/W2963227409","https://openalex.org/W2963253279","https://openalex.org/W2963503215","https://openalex.org/W2963823251","https://openalex.org/W2963917006","https://openalex.org/W2964218467","https://openalex.org/W2964343881","https://openalex.org/W2986050084","https://openalex.org/W2989035356","https://openalex.org/W2990806702","https://openalex.org/W3099406243","https://openalex.org/W4210257598"],"related_works":["https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2145649715","https://openalex.org/W2047313939","https://openalex.org/W2113666009","https://openalex.org/W3195209712","https://openalex.org/W1997160662"],"abstract_inverted_index":{"Video":[0],"Object":[1],"Segmentation":[2],"(VOS)":[3],"is":[4,24,54],"typically":[5],"formulated":[6],"in":[7,36,52,95,129,201],"a":[8,105,110,132,159,184],"semi-supervised":[9],"setting.":[10],"Given":[11],"the":[12,17,20,29,37,41,44,49,58,62,67,83,87,92,119,140,153,165],"ground-truth":[13],"segmentation":[14,166],"mask":[15],"on":[16,189],"first":[18],"frame,":[19],"task":[21],"of":[22,34,40,48,61,100,143,156,203],"VOS":[23,53,192],"to":[25,56,65,90],"track":[26],"and":[27,77,109,171,186,199,206],"segment":[28],"single":[30],"or":[31],"multiple":[32],"objects":[33],"interests":[35],"rest":[38],"frames":[39,128],"video":[42,79,130],"at":[43],"pixel":[45],"level.":[46],"One":[47],"fundamental":[50],"challenges":[51],"how":[55],"make":[57],"most":[59],"use":[60],"temporal":[63,88,93,102],"information":[64,81],"boost":[66],"performance.":[68],"We":[69],"present":[70],"an":[71],"end-to-end":[72],"network":[73,98],"which":[74,136],"stores":[75],"short-":[76],"long-term":[78,111,149],"sequence":[80],"preceding":[82],"current":[84],"frame":[85],"as":[86],"memories":[89],"address":[91],"modeling":[94],"VOS.":[96],"Our":[97],"consists":[99],"two":[101],"sub-networks":[103],"including":[104,194],"short-term":[106,115],"memory":[107,112,116,150],"sub-network":[108,117,151],"sub-network.":[113],"The":[114,148],"models":[118,152],"fine-grained":[120],"spatial-temporal":[121],"interactions":[122],"between":[123],"local":[124,144],"regions":[125,145],"across":[126],"neighboring":[127],"via":[131,158],"graph-based":[133],"learning":[134],"framework,":[135],"can":[137],"well":[138],"preserve":[139],"visual":[141],"consistency":[142],"over":[146],"time.":[147],"long-range":[154],"evolution":[155],"object":[157],"Simplified-Gated":[160],"Recurrent":[161],"Unit":[162],"(S-GRU),":[163],"making":[164],"be":[167],"robust":[168],"against":[169],"occlusions":[170],"drift":[172],"errors.":[173],"In":[174],"our":[175,180],"experiments,":[176],"we":[177],"show":[178],"that":[179],"proposed":[181],"method":[182],"achieves":[183],"favorable":[185],"competitive":[187],"performance":[188],"three":[190],"frequently-used":[191],"datasets,":[193],"DAVIS":[195,197],"2016,":[196],"2017":[198],"Youtube-VOS":[200],"terms":[202],"both":[204],"speed":[205],"accuracy.":[207]},"counts_by_year":[{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}