{"id":"https://openalex.org/W4375869407","doi":"https://doi.org/10.1109/icassp49357.2023.10094565","title":"Divcon: Learning Concept Sequences for Semantically Diverse Image Captioning","display_name":"Divcon: Learning Concept Sequences for Semantically Diverse Image Captioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869407","doi":"https://doi.org/10.1109/icassp49357.2023.10094565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5061840305","display_name":"Yue Zheng","orcid":"https://orcid.org/0000-0002-4992-6475"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zheng","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering","Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346266","display_name":"Yali Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Li Li","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering","Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030965866","display_name":"Shengjin Wang","orcid":"https://orcid.org/0000-0001-7809-1932"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjin Wang","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering","Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2428,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53887789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940999746322632,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9879000186920166,"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":0.9223542809486389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8189231157302856},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6180953979492188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6099081039428711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6070263385772705},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5571668148040771},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5261102318763733},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5127333402633667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4492158889770508},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3352256715297699}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9223542809486389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189231157302856},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6180953979492188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6099081039428711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6070263385772705},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5571668148040771},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5261102318763733},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5127333402633667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4492158889770508},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3352256715297699},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2578466053","https://openalex.org/W2613904329","https://openalex.org/W2745461083","https://openalex.org/W2753215597","https://openalex.org/W2938704169","https://openalex.org/W2949555952","https://openalex.org/W2963096510","https://openalex.org/W2970626077","https://openalex.org/W2982553922","https://openalex.org/W2988793532","https://openalex.org/W3007120620","https://openalex.org/W3097062010","https://openalex.org/W3107848485","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6687483927","https://openalex.org/W6725318829","https://openalex.org/W6728274705","https://openalex.org/W6732875994","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6744104549","https://openalex.org/W6761551260","https://openalex.org/W6767459567","https://openalex.org/W6773707559","https://openalex.org/W6780975476","https://openalex.org/W6785276314"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3145906801"],"abstract_inverted_index":{"Human":[0],"generated":[1],"image":[2,57,130],"captions":[3,113],"contain":[4],"diverse":[5,56,63,115,129],"semantic":[6,21,36,44,64,116],"concepts,":[7,37],"while":[8],"this":[9,47],"is":[10,25],"still":[11],"a":[12,40,51,70,87,92],"difficult":[13],"task":[14],"for":[15,55,104],"machines.":[16],"The":[17],"frequency":[18],"distribution":[19],"of":[20,147],"concepts":[22,65,117],"in":[23,39,42,86],"datasets":[24],"usually":[26],"extremely":[27],"imbalanced,":[28],"leading":[29],"to":[30,74,122],"models":[31],"repeatedly":[32],"describe":[33],"frequently":[34],"occurring":[35,125],"resulting":[38],"decline":[41],"the":[43,81,98,123,128,135],"diversity.":[45],"In":[46,127],"paper,":[48],"we":[49,68],"propose":[50],"novel":[52],"two-step":[53],"method":[54],"captioning,":[58],"generating":[59],"descriptions":[60,103],"with":[61,141],"more":[62,120],"(Di-vCon).":[66],"Firstly,":[67],"developed":[69],"concept":[71,77,99],"sequence":[72],"generator":[73,94],"auto-regressively":[75],"generate":[76,112],"sequences.":[78],"This":[79],"benefits":[80],"model":[82],"by":[83],"decoding":[84],"sequences":[85,100],"small":[88],"searching":[89],"space.":[90],"Then":[91],"sentence":[93],"takes":[95],"as":[96],"input":[97],"and":[101,118,144,149],"generates":[102],"each":[105],"sequence.":[106],"Experiments":[107],"show":[108],"that":[109],"DivCon":[110],"can":[111],"containing":[114],"pay":[119],"attention":[121],"less":[124],"concepts.":[126],"captioning":[131],"task,":[132],"Div-Con":[133],"achieves":[134],"state-of-the-art":[136],"results":[137],"on":[138],"MSCOCO":[139],"dataset":[140],"oracle":[142],"CIDEr":[143],"SPICE":[145],"scores":[146],"1.684":[148],"0.302.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}