{"id":"https://openalex.org/W4304084115","doi":"https://doi.org/10.1145/3503161.3547761","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","display_name":"Multi-Attention Network for Compressed Video Referring Object Segmentation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084115","doi":"https://doi.org/10.1145/3503161.3547761"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547761","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547761","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547761","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547761","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100357392","display_name":"Weidong Chen","orcid":"https://orcid.org/0000-0003-2774-2875"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Chen","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031477293","display_name":"Dexiang Hong","orcid":"https://orcid.org/0000-0001-7468-073X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexiang Hong","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000034551","display_name":"Zhenjun Han","orcid":"https://orcid.org/0000-0002-9970-5152"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjun Han","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010557705","display_name":"Laiyun Qing","orcid":"https://orcid.org/0000-0001-9923-5034"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Laiyun Qing","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100775216","display_name":"Guorong Li","orcid":"https://orcid.org/0000-0003-3954-2387"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorong Li","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4416","last_page":"4425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9994999766349792,"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":0.8439716100692749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7123068571090698},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6233907341957092},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5515923500061035},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5492881536483765},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.43534910678863525},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38287803530693054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439716100692749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7123068571090698},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6233907341957092},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5515923500061035},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5492881536483765},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.43534910678863525},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38287803530693054}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547761","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547761","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547761","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3547761","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547761","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547761","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1590744552","display_name":null,"funder_award_id":"61872333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5327851226","display_name":null,"funder_award_id":"62022083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5967673014","display_name":null,"funder_award_id":"61976069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6117202374","display_name":null,"funder_award_id":"2018YFE0118400","funder_id":"https://openalex.org/F4320335892","funder_display_name":"Youth Innovation Promotion Association"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":"\u57fa\u4e8e\u5927\u89c4\u6a21\u8de8\u5a92\u4f53\u77e5\u8bc6\u7f51\u7edc\u7684\u590d\u6742\u89c6\u9891\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7801426869","display_name":"\u7aef\u4e91\u534f\u540c\u89c6\u9891\u667a\u80fd\u8ba1\u7b97\u65b9\u6cd5\u4e0e\u82af\u7247\u67b6\u6784\u7814\u7a76","funder_award_id":"61931008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G791984389","display_name":null,"funder_award_id":"61902092","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304084115.pdf","grobid_xml":"https://content.openalex.org/works/W4304084115.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1905722737","https://openalex.org/W2194775991","https://openalex.org/W2342776425","https://openalex.org/W2734973448","https://openalex.org/W2767179670","https://openalex.org/W2782776028","https://openalex.org/W2896798564","https://openalex.org/W2955058313","https://openalex.org/W2963091558","https://openalex.org/W2963094665","https://openalex.org/W2963354481","https://openalex.org/W2963370182","https://openalex.org/W2963560969","https://openalex.org/W2963901365","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2980088508","https://openalex.org/W2981165461","https://openalex.org/W2981851019","https://openalex.org/W2983693499","https://openalex.org/W3034777757","https://openalex.org/W3034804856","https://openalex.org/W3092651603","https://openalex.org/W3092708970","https://openalex.org/W3093154363","https://openalex.org/W3093174808","https://openalex.org/W3093200502","https://openalex.org/W3093246508","https://openalex.org/W3093385053","https://openalex.org/W3095718427","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3122784054","https://openalex.org/W3133092047","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3161888766","https://openalex.org/W3171516518","https://openalex.org/W3177892185","https://openalex.org/W3178075329","https://openalex.org/W3187240237","https://openalex.org/W3202778561","https://openalex.org/W3206261212","https://openalex.org/W3207798279","https://openalex.org/W3215899623","https://openalex.org/W4300424419"],"related_works":["https://openalex.org/W4389065903","https://openalex.org/W2385949326","https://openalex.org/W2012200063","https://openalex.org/W2623195638","https://openalex.org/W1966005655","https://openalex.org/W3135795035","https://openalex.org/W2789220062","https://openalex.org/W2811496562","https://openalex.org/W2094665863","https://openalex.org/W2071984725"],"abstract_inverted_index":{"Referring":[0],"video":[1,20,82,91,102],"object":[2,8,71,93,175],"segmentation":[3,94,187],"aims":[4],"to":[5,22,25,135,173,177,184,195],"segment":[6],"the":[7,40,69,80,86,90,129,157,167,203,220],"referred":[9],"by":[10],"a":[11,113,123,179],"given":[12],"language":[13],"expression.":[14],"Existing":[15],"works":[16],"typically":[17],"require":[18],"compressed":[19,76,101,140],"bitstream":[21],"be":[23],"decoded":[24],"RGB":[26,235],"frames":[27],"before":[28],"being":[29],"segmented,":[30],"which":[31,116,200,230],"increases":[32],"computation":[33],"and":[34,37,58,122,149,162,165,183],"storage":[35],"requirements":[36],"ultimately":[38],"slows":[39],"inference":[41],"down.":[42],"This":[43],"may":[44],"hamper":[45],"its":[46],"application":[47],"in":[48,64,142],"real-world":[49],"computing":[50],"resource":[51],"limited":[52],"scenarios,":[53],"such":[54],"as":[55],"autonomous":[56],"cars":[57],"drones.":[59],"To":[60,107],"alleviate":[61],"this":[62,65,109],"problem,":[63,110],"paper,":[66],"we":[67,111,193],"explore":[68],"referring":[70,92],"segmenta-":[72],"tion":[73],"task":[74,95],"on":[75,79,215],"videos,":[77],"namely":[78],"original":[81],"data":[83,141],"flow.":[84],"Besides":[85],"inherent":[87],"difficulty":[88],"of":[89,118,208,222],"itself,":[96],"obtaining":[97],"discriminative":[98],"representation":[99,138],"from":[100,139,190],"is":[103,133,239],"also":[104],"rather":[105],"challenging.":[106],"address":[108],"propose":[112,194],"multi-attention":[114],"network":[115],"consists":[117],"dual-path":[119,130],"dual-attention":[120,131],"module":[121,132],"query-based":[124,152],"cross-modal":[125,153],"Transformer":[126,154],"module.":[127],"Specifically,":[128],"designed":[134],"extract":[136],"effective":[137],"three":[143,216],"modalities,":[144,164],"i.e.,":[145],"I-frame,":[146],"Motion":[147],"Vector":[148],"Residual.":[150],"The":[151],"firstly":[155],"models":[156],"corre-":[158],"lation":[159],"between":[160],"linguistic":[161],"visual":[163],"then":[166],"fused":[168],"multi-modality":[169],"features":[170],"are":[171,231],"used":[172],"guide":[174],"queries":[176],"generate":[178],"content-aware":[180],"dynamic":[181],"kernel":[182],"predict":[185],"final":[186],"masks.":[188],"Different":[189],"previous":[191],"works,":[192],"learn":[196],"just":[197],"one":[198],"kernel,":[199],"thus":[201],"removes":[202],"complicated":[204],"post":[205],"mask-matching":[206],"procedure":[207],"existing":[209],"methods.":[210],"Extensive":[211],"promising":[212],"experimental":[213],"results":[214],"challenging":[217],"datasets":[218],"show":[219],"effectiveness":[221],"our":[223],"method":[224],"compared":[225],"against":[226],"several":[227],"state-of-the-art":[228],"methods":[229],"proposed":[232],"for":[233],"processing":[234],"data.":[236],"Source":[237],"code":[238],"available":[240],"at:":[241],"https://github.com/DexiangHong/MANet.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}