{"id":"https://openalex.org/W2767057417","doi":"https://doi.org/10.1145/3123266.3123275","title":"StructCap","display_name":"StructCap","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2767057417","doi":"https://doi.org/10.1145/3123266.3123275","mag":"2767057417"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123275","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008400844","display_name":"Fuhai Chen","orcid":"https://orcid.org/0000-0001-5441-5998"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuhai Chen","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066326238","display_name":"Jinsong Su","orcid":"https://orcid.org/0000-0001-5606-7122"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716576","display_name":"Yongjian Wu","orcid":"https://orcid.org/0000-0003-2007-6929"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Wu","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091425569","display_name":"Yunsheng Wu","orcid":"https://orcid.org/0000-0001-7462-1414"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsheng Wu","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9815000295639038,"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":0.4503431022167206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4503431022167206}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123275","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1423339008","https://openalex.org/W1514535095","https://openalex.org/W1785460851","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1915480574","https://openalex.org/W1938976761","https://openalex.org/W1947481528","https://openalex.org/W1980124385","https://openalex.org/W2064675550","https://openalex.org/W2076874408","https://openalex.org/W2101105183","https://openalex.org/W2104125540","https://openalex.org/W2117539524","https://openalex.org/W2118020555","https://openalex.org/W2124592697","https://openalex.org/W2133564696","https://openalex.org/W2139380585","https://openalex.org/W2139381543","https://openalex.org/W2143017621","https://openalex.org/W2171048379","https://openalex.org/W2171361956","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2519205375","https://openalex.org/W2545985378","https://openalex.org/W2550553598","https://openalex.org/W2565165987","https://openalex.org/W2604522653","https://openalex.org/W2613718673","https://openalex.org/W2756565784","https://openalex.org/W2913081710","https://openalex.org/W2949888546","https://openalex.org/W2953106684","https://openalex.org/W2953158660","https://openalex.org/W2962935746","https://openalex.org/W2963048156","https://openalex.org/W2963418361","https://openalex.org/W2964121744","https://openalex.org/W4251372957","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6685230081","https://openalex.org/W6730707965","https://openalex.org/W6736588697"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Image":[0],"captioning":[1,103,154],"has":[2],"attracted":[3],"ever-increasing":[4],"research":[5],"attention":[6,57,151],"in":[7,69,81,119],"multimedia":[8],"and":[9,53,71,76,115,127,152,164],"computer":[10],"vision.":[11],"To":[12],"encode":[13,50],"the":[14,21,62,86,168,173],"visual":[15,31,51,121,134,146],"content,":[16],"existing":[17],"approaches":[18,175],"typically":[19],"utilize":[20],"off-the-shelf":[22],"deep":[23],"Convolutional":[24],"Neural":[25,38],"Network":[26,39],"(CNN)":[27],"model":[28,171],"to":[29,36,44,91,141],"extract":[30],"features,":[32],"which":[33,79,124],"are":[34,80],"sent":[35],"Recurrent":[37],"(RNN)":[40],"based":[41],"textual":[42],"generators":[43],"output":[45],"word":[46],"sequence.":[47],"Some":[48],"methods":[49],"objects":[52],"scene":[54],"information":[55],"with":[56],"mechanism":[58],"more":[59],"recently.":[60],"Despite":[61],"promising":[63],"progress,":[64],"one":[65],"distinct":[66],"disadvantage":[67],"lies":[68],"distinguishing":[70],"modeling":[72],"key":[73,113],"semantic":[74,150],"entities":[75,114],"their":[77,116],"relations,":[78],"turn":[82],"widely":[83],"regarded":[84],"as":[85],"important":[87],"cues":[88],"for":[89],"us":[90],"describe":[92],"image":[93,102,111],"content.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98],"propose":[99],"a":[100,109,120],"novel":[101],"model,":[104],"termed":[105],"StructCap.":[106],"It":[107],"parses":[108],"given":[110],"into":[112],"relations":[117],"organized":[118],"parsing":[122],"tree,":[123],"is":[125],"transformed":[126],"embedded":[128],"under":[129,176],"an":[130,138],"encoder-decoder":[131],"framework":[132],"via":[133],"attention.":[135],"We":[136],"give":[137],"end-to-end":[139],"formulation":[140],"facilitate":[142],"joint":[143],"training":[144],"of":[145],"tree":[147],"parser,":[148],"structured":[149],"RNN-based":[153],"modules.":[155],"Experimental":[156],"results":[157],"on":[158],"two":[159],"public":[160],"benchmarks,":[161],"Microsoft":[162],"COCO":[163],"Flickr30K,":[165],"show":[166],"that":[167],"proposed":[169],"StructCap":[170],"outperforms":[172],"state-of-the-art":[174],"various":[177],"standard":[178],"evaluation":[179],"metrics.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2017-11-10T00:00:00"}