{"id":"https://openalex.org/W4392903958","doi":"https://doi.org/10.1109/icassp48485.2024.10446104","title":"Multi-Source Dynamic Interactive Network Collaborative Reasoning Image Captioning","display_name":"Multi-Source Dynamic Interactive Network Collaborative Reasoning Image Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903958","doi":"https://doi.org/10.1109/icassp48485.2024.10446104"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446104","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/A5072565311","display_name":"Qiang Su","orcid":"https://orcid.org/0000-0003-0755-5802"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiang Su","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072565311"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02684031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8010","last_page":"8014"},"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":0.9918000102043152,"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":0.9854000210762024,"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":0.8831850290298462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8563075065612793},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6025081872940063},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6024731993675232},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5737705230712891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5621121525764465},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5400077104568481},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4989931583404541},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4964917302131653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40303534269332886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3821013569831848},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3593136668205261},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3252364993095398}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8831850290298462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8563075065612793},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6025081872940063},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6024731993675232},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5737705230712891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621121525764465},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5400077104568481},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4989931583404541},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4964917302131653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40303534269332886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3821013569831848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3593136668205261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3252364993095398},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446104","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":[],"awards":[{"id":"https://openalex.org/G1153685412","display_name":null,"funder_award_id":"61966004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2214335821","display_name":null,"funder_award_id":"2019GXNSF","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4562351609","display_name":null,"funder_award_id":"61966004","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G4762191740","display_name":null,"funder_award_id":"62276073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6096834954","display_name":null,"funder_award_id":"2019GXNSFDA245018","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963101956","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3096407995","https://openalex.org/W3173220247","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W3216224027","https://openalex.org/W4205357838","https://openalex.org/W4214917601","https://openalex.org/W4280622456","https://openalex.org/W4288043227","https://openalex.org/W4312924260","https://openalex.org/W6638742206","https://openalex.org/W6763643401","https://openalex.org/W6775970589","https://openalex.org/W6791353385","https://openalex.org/W6811013733","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Rich":[0],"image":[1,11,16,52,64,84,105],"and":[2,17,38,45,53,65,85,106,131],"text":[3,18,54,66,86],"features":[4,19,55,67,157],"can":[5,186],"largely":[6],"improve":[7],"the":[8,21,40,49,78,82,93,97,114,138,144,153,161,165,168,172,184,190],"training":[9],"of":[10,23,27,51,63,74,80,96,167,179],"captioning":[12],"tasks.":[13],"However,":[14],"rich":[15],"mean":[20],"incorporation":[22],"a":[24,57,72,121,126,132,147],"large":[25],"amount":[26],"unnecessary":[28],"information.":[29],"In":[30],"our":[31],"work,":[32],"in":[33,43,89,110],"order":[34,90],"to":[35,91,151,158,160,193],"fully":[36,188],"explore":[37],"utilize":[39,189],"key":[41],"information":[42],"images":[44],"text,":[46,107],"we":[47],"view":[48],"combination":[50,62],"as":[56],"data":[58],"screening":[59],"problem.":[60],"The":[61],"is":[68],"dynamically":[69],"screened":[70],"through":[71],"series":[73],"inference":[75],"strategies":[76],"with":[77],"aim":[79],"selecting":[81],"optimal":[83],"features.":[87],"First,":[88],"enhance":[92],"prior":[94],"knowledge":[95],"model,":[98],"three":[99,117],"input":[100,159],"features,":[101],"grid":[102],"image,":[103],"region":[104],"are":[108],"designed":[109],"this":[111],"paper.":[112],"Second,":[113],"model":[115,145],"designs":[116],"feature":[118,128],"enhancement":[119,124,129,135,156],"channels,":[120],"global":[122],"scene":[123],"channel,":[125,136],"regional":[127],"channel":[130],"multimodal":[133],"semantic":[134],"for":[137],"multi-source":[139],"dynamic":[140,148],"interaction":[141],"network.":[142],"Finally,":[143],"uses":[146],"selection":[149],"mechanism":[150],"choose":[152],"most":[154],"appropriate":[155],"decoder.":[162],"We":[163],"validate":[164],"effectiveness":[166],"approach":[169],"by":[170],"comparing":[171],"baseline":[173],"model.":[174],"Moreover,":[175],"an":[176],"in-depth":[177],"analysis":[178],"each":[180],"module":[181],"demonstrates":[182],"that":[183],"method":[185],"more":[187],"current":[191],"resources":[192],"achieve":[194],"better":[195],"results.":[196]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}