{"id":"https://openalex.org/W2965820511","doi":"https://doi.org/10.24963/ijcai.2019/726","title":"Swell-and-Shrink: Decomposing Image Captioning by Transformation and Summarization","display_name":"Swell-and-Shrink: Decomposing Image Captioning by Transformation and Summarization","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965820511","doi":"https://doi.org/10.24963/ijcai.2019/726","mag":"2965820511"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/726","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/726","pdf_url":"https://www.ijcai.org/proceedings/2019/0726.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0726.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101670955","display_name":"Hanzhang Wang","orcid":"https://orcid.org/0009-0006-4088-5984"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzhang Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101839579","display_name":"Kaisheng Xu","orcid":"https://orcid.org/0000-0002-7455-8352"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisheng Xu","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5226","last_page":"5232"},"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":0.995199978351593,"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":0.9932000041007996,"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":0.9810621738433838},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8138519525527954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788767397403717},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7852001786231995},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6949771046638489},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6284746527671814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5967500805854797},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5311193466186523},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5170326828956604},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4526025652885437},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.44642212986946106},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41468632221221924},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4134376049041748},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37288224697113037},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3594278395175934}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9810621738433838},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8138519525527954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788767397403717},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7852001786231995},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6949771046638489},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6284746527671814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5967500805854797},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5311193466186523},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5170326828956604},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4526025652885437},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.44642212986946106},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41468632221221924},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4134376049041748},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37288224697113037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3594278395175934},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/726","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/726","pdf_url":"https://www.ijcai.org/proceedings/2019/0726.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/726","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/726","pdf_url":"https://www.ijcai.org/proceedings/2019/0726.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G740467349","display_name":null,"funder_award_id":"61622115","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965820511.pdf","grobid_xml":"https://content.openalex.org/works/W2965820511.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2070150502","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2133564696","https://openalex.org/W2277195237","https://openalex.org/W2288604516","https://openalex.org/W2307381258","https://openalex.org/W2526471240","https://openalex.org/W2549599535","https://openalex.org/W2552002300","https://openalex.org/W2564898401","https://openalex.org/W2574535369","https://openalex.org/W2604729005","https://openalex.org/W2605045867","https://openalex.org/W2745461083","https://openalex.org/W2952138241","https://openalex.org/W2962762898","https://openalex.org/W2962965405","https://openalex.org/W2963649796","https://openalex.org/W2963686907","https://openalex.org/W2963758027","https://openalex.org/W2963929190","https://openalex.org/W2964018924","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2905433371","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4284703357"],"abstract_inverted_index":{"Image":[0],"captioning":[1,55],"is":[2,50,73],"currently":[3],"viewed":[4],"as":[5,32,56],"a":[6,47,57,89],"problem":[7],"analogous":[8],"to":[9,52,75,122],"machine":[10],"translation.":[11],"However,":[12],"it":[13],"always":[14,38],"suffers":[15],"from":[16],"poor":[17],"interpretability,":[18],"coarse":[19],"or":[20],"even":[21],"incorrect":[22],"descriptions":[23],"on":[24,95,134],"regional":[25,131],"details.":[26],"Moreover,":[27],"information":[28],"abstraction":[29],"and":[30,40,68,102,111,117],"compression,":[31],"essential":[33],"characteristics":[34],"of":[35,62,88,113,115,125,130,141],"captioning,":[36],"are":[37,120],"overlooked":[39],"seldom":[41],"discussed.":[42],"To":[43],"overcome":[44],"the":[45,85,97,104,109,128,139,142],"shortcomings,":[46],"swell-shrink":[48],"method":[49],"proposed":[51,143],"redefine":[53],"image":[54],"compositional":[58],"task":[59],"which":[60,92],"consists":[61,87],"two":[63],"separated":[64],"modules:":[65],"modality":[66,118],"transformation":[67],"text":[69],"compression.":[70],"The":[71],"former":[72],"guaranteed":[74],"accurately":[76],"transform":[77],"adequate":[78],"visual":[79,132],"content":[80],"into":[81],"textual":[82],"form":[83],"while":[84],"latter":[86],"hierarchical":[90],"LSTM":[91],"particularly":[93],"emphasizes":[94],"removing":[96],"redundancy":[98],"among":[99],"multiple":[100],"phrases":[101],"organizing":[103],"final":[105],"abstractive":[106],"caption.":[107],"Additionally,":[108],"order":[110],"quality":[112],"region":[114],"interest":[116],"processing":[119],"studied":[121],"give":[123],"insights":[124],"better":[126],"understanding":[127],"influence":[129],"cues":[133],"language":[135],"forming.":[136],"Experiments":[137],"demonstrate":[138],"effectiveness":[140],"method.":[144]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}