{"id":"https://openalex.org/W4304092583","doi":"https://doi.org/10.1145/3503161.3548024","title":"Progressive Tree-Structured Prototype Network for End-to-End Image Captioning","display_name":"Progressive Tree-Structured Prototype Network for End-to-End Image Captioning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092583","doi":"https://doi.org/10.1145/3503161.3548024"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548024","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548024","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074820902","display_name":"Jinkuan Zhu","orcid":"https://orcid.org/0000-0001-7360-7119"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinkuan Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China & Peng Cheng Laboratory, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Peng Cheng Laboratory, Chengdu, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"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":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5210","last_page":"5218"},"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":0.9948999881744385,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9934999942779541,"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/closed-captioning","display_name":"Closed captioning","score":0.8770793080329895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8607242703437805},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5701133012771606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5663893222808838},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5574589967727661},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5515619516372681},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.497560054063797},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4709043502807617},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.449422150850296},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4118443727493286},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3014441728591919},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13162937760353088}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8770793080329895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607242703437805},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5701133012771606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5663893222808838},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5574589967727661},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5515619516372681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.497560054063797},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4709043502807617},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.449422150850296},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4118443727493286},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3014441728591919},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13162937760353088},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548024","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548024","pdf_url":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1355643883","display_name":null,"funder_award_id":"No. 62020106008, No. 62122018, No. 61772116, No. 61872064","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2150593711","https://openalex.org/W2277195237","https://openalex.org/W2339652278","https://openalex.org/W2463955103","https://openalex.org/W2745461083","https://openalex.org/W2808138519","https://openalex.org/W2895902247","https://openalex.org/W2963084599","https://openalex.org/W2963187678","https://openalex.org/W2974497444","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3087338569","https://openalex.org/W3134272453","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W3205071568","https://openalex.org/W3205607545","https://openalex.org/W3207608362","https://openalex.org/W3207942052","https://openalex.org/W3214744507","https://openalex.org/W4221147537","https://openalex.org/W4285602612","https://openalex.org/W4313131769","https://openalex.org/W6791103873"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Studies":[0],"of":[1,9,94,119,187],"image":[2,153],"captioning":[3,163],"are":[4],"shifting":[5],"towards":[6],"a":[7,10,76,109,117,143,176],"trend":[8],"fully":[11],"end-to-end":[12,162],"paradigm":[13],"by":[14,100],"leveraging":[15],"powerful":[16],"visual":[17,66,138],"pre-trained":[18],"models":[19,210],"and":[20,29,68,154,184,195,198,211],"transformer-based":[21],"generation":[22],"architecture":[23],"for":[24],"more":[25],"flexible":[26],"model":[27],"training":[28],"faster":[30],"inference":[31],"speed.":[32],"State-of-the-art":[33],"approaches":[34,47],"simply":[35],"extract":[36],"isolated":[37],"concepts":[38],"or":[39],"attributes":[40],"to":[41,61,89,147,160],"assist":[42],"description":[43],"generation.":[44],"However,":[45],"such":[46,134],"do":[48],"not":[49],"consider":[50],"the":[51,56,86,92,102,125,152,161,204],"hierarchical":[52,103,120,126],"semantic":[53,127,149],"structure":[54,128],"in":[55,129],"textual":[57,104,130],"domain,":[58],"which":[59,84,123],"leads":[60],"an":[62],"unpredictable":[63],"mapping":[64],"between":[65],"representations":[67],"concept":[69],"words.":[70],"To":[71,132],"this":[72],"end,":[73],"we":[74,107,140],"propose":[75,142],"novel":[77,110],"Progressive":[78],"Tree-Structured":[79],"prototype":[80],"Network":[81],"(dubbed":[82],"PTSN),":[83],"is":[85],"first":[87],"attempt":[88],"narrow":[90],"down":[91],"scope":[93],"prediction":[95],"words":[96],"with":[97,180],"appropriate":[98],"semantics":[99],"modeling":[101],"semantics.":[105],"Specifically,":[106],"design":[108],"embedding":[111],"method":[112,174],"called":[113],"tree-structured":[114,135],"prototype,":[115],"producing":[116],"set":[118],"representative":[121],"embeddings":[122],"capture":[124],"space.":[131],"utilize":[133],"prototypes":[136],"into":[137],"cognition,":[139],"also":[141],"progressive":[144],"aggregation":[145],"module":[146],"exploit":[148],"relationships":[150],"within":[151],"prototypes.":[155],"By":[156],"applying":[157],"our":[158,173],"PTSN":[159],"framework,":[164],"extensive":[165],"experiments":[166],"conducted":[167],"on":[168,192,203],"MSCOCO":[169],"dataset":[170],"show":[171],"that":[172],"achieves":[175],"new":[177],"state-of-the-art":[178],"performance":[179],"144.2%":[181],"(single":[182],"model)":[183],"146.5%":[185],"(ensemble":[186],"4":[188],"models)":[189],"CIDEr":[190,201],"scores":[191,202],"'Karpathy'":[193],"split":[194],"141.4%":[196],"(c5)":[197],"143.9%":[199],"(c40)":[200],"official":[205],"online":[206],"test":[207],"server.":[208],"Trained":[209],"source":[212],"code":[213],"have":[214],"been":[215],"released":[216],"at:":[217],"https://github.com/NovaMind-Z/PTSN.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}