{"id":"https://openalex.org/W4392902900","doi":"https://doi.org/10.1109/icassp48485.2024.10446024","title":"Think as People: Context-Driven Multi-Image News Captioning with Adaptive Dual Attention","display_name":"Think as People: Context-Driven Multi-Image News Captioning with Adaptive Dual Attention","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902900","doi":"https://doi.org/10.1109/icassp48485.2024.10446024"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446024","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100636291","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0002-3211-5369"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","King Abdullah University of Science and Technology, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031533573","display_name":"Xiaodong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Xiaodong Wu","raw_affiliation_strings":["King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","King Abdullah University of Science and Technology, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110999110","display_name":"Xiuying Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Xiuying Chen","raw_affiliation_strings":["King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","King Abdullah University of Science and Technology, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618900","display_name":"Xin Gao","orcid":"https://orcid.org/0000-0002-7108-3574"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Xin Gao","raw_affiliation_strings":["King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","King Abdullah University of Science and Technology, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology,Jeddah,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA","US"],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","raw_affiliation_strings":["University of Notre Dame,Indiana,United States","King Abdullah University of Science and Technology, Saudi Arabia","University of Notre Dame, Indiana, United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Indiana,United States","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"University of Notre Dame, Indiana, United States","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100636291"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02538071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4430","last_page":"4434"},"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":0.9969000220298767,"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/T11439","display_name":"Video Analysis and Summarization","score":0.98580002784729,"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":0.9934673309326172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7844427824020386},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7192203402519226},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6418521404266357},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5979387760162354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4726387858390808},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4695257246494293},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33736854791641235},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0894005298614502}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9934673309326172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844427824020386},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7192203402519226},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6418521404266357},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5979387760162354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4726387858390808},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4695257246494293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33736854791641235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0894005298614502},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446024","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2804552794","https://openalex.org/W2945755204","https://openalex.org/W2963084599","https://openalex.org/W2982573303","https://openalex.org/W2986670728","https://openalex.org/W2996421194","https://openalex.org/W3034689697","https://openalex.org/W3036848992","https://openalex.org/W3096440661","https://openalex.org/W3100932507","https://openalex.org/W3115803208","https://openalex.org/W3183226462","https://openalex.org/W3211405508","https://openalex.org/W4200518184","https://openalex.org/W4206675125","https://openalex.org/W4231299465","https://openalex.org/W4384642280","https://openalex.org/W6630875275","https://openalex.org/W6682631176","https://openalex.org/W6751820907","https://openalex.org/W6763643401","https://openalex.org/W6779919487","https://openalex.org/W6804675693","https://openalex.org/W6898505805"],"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/W2352553236"],"abstract_inverted_index":{"Automatic":[0],"image":[1,79,127],"captioning":[2,20,50,128,132],"has":[3,27],"been":[4,28],"extensively":[5],"studied,":[6],"however,":[7],"existing":[8],"methods":[9,129],"primarily":[10],"focus":[11],"on":[12,113],"a":[13,47,59],"single":[14],"image.":[15],"Actually,":[16],"the":[17,85,103,108,125],"demand":[18],"for":[19,52,70,77,101],"multiple":[21],"images":[22],"and":[23,38,74,87,96,106],"corresponding":[24],"contextual":[25],"information":[26],"growing":[29],"in":[30,130],"diverse":[31],"scenarios,":[32],"e.g.,":[33],"composing":[34],"news":[35],"articles":[36],"headlines,":[37],"electronic":[39],"medical":[40],"reports.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"novel":[48],"COntext-driven":[49],"approach":[51],"Multi-Image":[53],"News,":[54],"called":[55,63],"COMIN,":[56],"which":[57],"employs":[58],"two-step":[60],"attention":[61,69,76,95,98],"mechanism,":[62],"adaptive":[64],"dual":[65],"attention,":[66],"comprising":[67],"global":[68,94],"grasping":[71],"overall":[72],"context":[73],"local":[75,97],"finer":[78],"details.":[80],"It":[81],"is":[82],"inspired":[83],"by":[84],"observation":[86],"cognitive":[88],"processes":[89],"of":[90],"human":[91],"beings":[92],"where":[93],"are":[99],"responsible":[100],"understanding":[102],"high-level":[104],"features":[105],"detailing":[107],"low-level":[109],"features.":[110],"Experimental":[111],"results":[112],"our":[114,121],"newly":[115],"contributed":[116],"Star-News":[117],"dataset":[118],"show":[119],"that":[120],"proposed":[122],"model":[123],"outperforms":[124],"state-of-the-art":[126],"multi-image":[131],"scenarios.":[133]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
