{"id":"https://openalex.org/W3156800342","doi":"https://doi.org/10.1109/tmm.2021.3074008","title":"Structured Attention Network for Referring Image Segmentation","display_name":"Structured Attention Network for Referring Image Segmentation","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3156800342","doi":"https://doi.org/10.1109/tmm.2021.3074008","mag":"3156800342"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3074008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3074008","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077201605","display_name":"Pengxiang Yan","orcid":"https://orcid.org/0000-0002-3075-2903"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxiang Yan","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3075-2903","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101730408","display_name":"Xiaoqian Xu","orcid":"https://orcid.org/0000-0003-0391-0651"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqian Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012166205","display_name":"Sibei Yang","orcid":"https://orcid.org/0000-0002-8144-7351"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sibei Yang","raw_affiliation_strings":["Department of Computing, the Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, the Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Zeng","orcid":"https://orcid.org/0000-0002-6258-983X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6258-983X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042965510","display_name":"Guanbin Li","orcid":"https://orcid.org/0000-0002-4805-0926"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","Pazhou Laboratory, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4805-0926","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Pazhou Laboratory, Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.202,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.93298504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"24","issue":null,"first_page":"1922","last_page":"1932"},"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":0.9987999796867371,"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":0.9980999827384949,"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":0.8703357577323914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6390302181243896},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6364473104476929},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.574237585067749},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5711105465888977},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5705234408378601},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5607962608337402},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.532684862613678},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5206400752067566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49424460530281067},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4820719361305237},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4612061381340027},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4423673748970032},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4358384609222412},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42352694272994995},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4201188087463379},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07183650135993958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8703357577323914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6390302181243896},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6364473104476929},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.574237585067749},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5711105465888977},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5705234408378601},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5607962608337402},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.532684862613678},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5206400752067566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49424460530281067},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4820719361305237},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4612061381340027},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4423673748970032},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4358384609222412},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42352694272994995},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4201188087463379},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07183650135993958},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3074008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3074008","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1874218645","display_name":null,"funder_award_id":"61976250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3577923441","display_name":null,"funder_award_id":"U1811463","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1485009520","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1923211482","https://openalex.org/W2006147162","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2131774270","https://openalex.org/W2157331557","https://openalex.org/W2161236525","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2250861254","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2342543219","https://openalex.org/W2412782625","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2605127024","https://openalex.org/W2630837129","https://openalex.org/W2739107216","https://openalex.org/W2753311918","https://openalex.org/W2787091153","https://openalex.org/W2788810331","https://openalex.org/W2792265253","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2899771611","https://openalex.org/W2946086442","https://openalex.org/W2960655175","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963355447","https://openalex.org/W2963717374","https://openalex.org/W2963722138","https://openalex.org/W2963735856","https://openalex.org/W2964345792","https://openalex.org/W2980088508","https://openalex.org/W2984121207","https://openalex.org/W3004019157","https://openalex.org/W3006154882","https://openalex.org/W3034325957","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3099884890","https://openalex.org/W3102887392","https://openalex.org/W3108748824","https://openalex.org/W4293584584","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6739696289","https://openalex.org/W6740164494","https://openalex.org/W6750227808","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W579810227","https://openalex.org/W2968543375","https://openalex.org/W2098784136","https://openalex.org/W4288558800","https://openalex.org/W2953770453","https://openalex.org/W2888625260","https://openalex.org/W2293063786","https://openalex.org/W2911292476","https://openalex.org/W2741631785"],"abstract_inverted_index":{"Referring":[0],"image":[1],"segmentation":[2],"aims":[3],"at":[4],"segmenting":[5],"out":[6],"the":[7,25,66,70,75,81,105,113,127],"object":[8],"or":[9],"stuff":[10],"referred":[11],"to":[12,64],"by":[13],"a":[14,37,59,93],"natural":[15],"language":[16],"expression.":[17,77],"The":[18,33],"challenge":[19],"of":[20,27,36,129],"this":[21,55],"task":[22],"lies":[23],"in":[24,92],"requirement":[26],"understanding":[28],"both":[29],"vision":[30],"and":[31,44,51],"language.":[32],"linguistic":[34,52],"structure":[35],"referring":[38,76],"expression":[39],"can":[40],"provide":[41],"an":[42,85],"intuitive":[43],"explainable":[45,135],"layout":[46],"for":[47,98],"reasoning":[48,68,83],"over":[49,69],"visual":[50],"concepts.":[53],"In":[54,96],"paper,":[56],"we":[57],"propose":[58],"structured":[60],"attention":[61],"network":[62],"(SANet)":[63],"explore":[65],"multimodal":[67,82,87],"dependency":[71],"tree":[72],"parsed":[73],"from":[74],"Specifically,":[78],"SANet":[79,102,132],"implements":[80],"using":[84,112],"attentional":[86,115],"tree-structure":[88],"recurrent":[89],"module":[90],"(AMTreeGRU)":[91],"bottom-up":[94],"manner.":[95],"addition,":[97],"spatial":[99],"detail":[100],"improvement,":[101],"further":[103],"incorporates":[104],"semantics-guided":[106],"low-level":[107],"features":[108],"into":[109],"high-level":[110],"ones":[111],"proposed":[114,131],"skip":[116],"connection":[117],"module.":[118],"Extensive":[119],"experiments":[120],"on":[121],"four":[122],"public":[123],"benchmark":[124],"datasets":[125],"demonstrate":[126],"superiority":[128],"our":[130],"with":[133],"more":[134],"visualization":[136],"examples.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-27T08:28:00.272161","created_date":"2025-10-10T00:00:00"}