{"id":"https://openalex.org/W4404609296","doi":"https://doi.org/10.1109/icmlca63499.2024.10753950","title":"Advanced Techniques for Chinese Image Captioning: Investigating Attention Mechanisms Based on Object Detection for Chinese Image Caption Generation","display_name":"Advanced Techniques for Chinese Image Captioning: Investigating Attention Mechanisms Based on Object Detection for Chinese Image Caption Generation","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4404609296","doi":"https://doi.org/10.1109/icmlca63499.2024.10753950"},"language":"en","primary_location":{"id":"doi:10.1109/icmlca63499.2024.10753950","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmlca63499.2024.10753950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Machine Learning and Computer Application (ICMLCA)","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":null,"display_name":"Yongbin Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbin Hua","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064870968","display_name":"P. Li","orcid":"https://orcid.org/0009-0000-5343-6607"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei'ang Li","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100525581","display_name":"Xiangjin Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjin Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036697116","display_name":"Hong Xu","orcid":"https://orcid.org/0000-0002-2787-5806"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology,Wuhan,Hubei,China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9853000044822693,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9524000287055969,"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":0.9688901901245117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898349165916443},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6643948554992676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6429044008255005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5923343300819397},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5349814891815186},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4424899220466614},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.17703643441200256}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9688901901245117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898349165916443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6643948554992676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6429044008255005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5923343300819397},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5349814891815186},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4424899220466614},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.17703643441200256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlca63499.2024.10753950","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmlca63499.2024.10753950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Machine Learning and Computer Application (ICMLCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W2418300416","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2768477045","https://openalex.org/W2803525166","https://openalex.org/W6630875275"],"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/W4292830139"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,17,22,51,66,75,94],"image":[3,103],"caption":[4],"generation":[5,65,84],"aims":[6],"to":[7],"automatically":[8],"produce":[9],"natural":[10,26,67],"language":[11,27,68],"descriptions":[12],"that":[13],"match":[14],"the":[15,20,49,61,64,73,82,86],"content":[16],"images,":[18,60,95],"integrating":[19],"fields":[21],"machine":[23],"vision":[24],"and":[25,33,116],"processing,":[28],"which":[29],"holds":[30],"significant":[31],"theoretical":[32],"practical":[34],"value.":[35],"Inspired":[36],"by":[37],"top-down":[38],"attention":[39,46,79],"mechanisms,":[40],"this":[41,106],"paper":[42],"proposes":[43],"an":[44],"innovative":[45],"model.":[47],"Utilizing":[48],"output":[50],"pretrained":[52],"object":[53,76],"detection":[54,77],"networks":[55],"as":[56,78,114],"prior":[57],"knowledge":[58],"for":[59],"model":[62,87,107],"guides":[63],"descriptions.":[69],"By":[70],"directly":[71],"incorporating":[72],"results":[74],"inputs":[80],"into":[81],"text":[83],"network,":[85],"effectively":[88],"focuses":[89],"on":[90],"key":[91],"descriptive":[92],"regions":[93],"thereby":[96],"significantly":[97],"enhancing":[98],"performance.":[99],"On":[100],"public":[101],"Chinese":[102],"captioning":[104],"datasets,":[105],"demonstrates":[108],"substantial":[109],"advantages":[110],"in":[111],"metrics":[112],"such":[113],"BLEU-4":[115],"METEOR.":[117]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
