{"id":"https://openalex.org/W4414629165","doi":"https://doi.org/10.1145/3769866","title":"HIN: Hierarchical Interaction Network for Image Captioning","display_name":"HIN: Hierarchical Interaction Network for Image Captioning","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4414629165","doi":"https://doi.org/10.1145/3769866"},"language":"en","primary_location":{"id":"doi:10.1145/3769866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769866","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5111169554","display_name":"Chuanle Song","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanle Song","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","School of Electronics and Information Technology, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0009-0008-9893-6195","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059433400","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0002-9237-7205"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","School of Electronics and Information Technology, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0002-9237-7205","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109573014","display_name":"Han Yi Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jiao","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","School of Electronics and Information Technology, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0009-0003-2021-8015","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048231607","display_name":"Wenjin Huang","orcid":"https://orcid.org/0000-0002-8861-4263"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjin Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","School of Electronics and Information Technology, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0002-8861-4263","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junfeng Li","orcid":"https://orcid.org/0009-0004-8773-7765"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Li","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","School of Electronics and Information Technology, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0009-0004-8773-7765","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101448401","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0001-6736-7913"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","School of Electronics and Information Technology, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0001-6736-7913","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85125471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"21","issue":"12","first_page":"1","last_page":"22"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.9878000020980835,"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":0.8568999767303467},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.757099986076355},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6132000088691711},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6026999950408936},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5042999982833862},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4481000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8849999904632568},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8568999767303467},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.757099986076355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3619000017642975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769866","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5040486816","display_name":null,"funder_award_id":"2022A1515110006 and 2024A1515011259","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6701825051","display_name":null,"funder_award_id":"62276278","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2108598243","https://openalex.org/W2133459682","https://openalex.org/W2302086703","https://openalex.org/W2745461083","https://openalex.org/W2963084599","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3173220247","https://openalex.org/W3183824823","https://openalex.org/W3212847756","https://openalex.org/W4282968790","https://openalex.org/W4283722434","https://openalex.org/W4285186657","https://openalex.org/W4292828275","https://openalex.org/W4296124987","https://openalex.org/W4303444943","https://openalex.org/W4312289196","https://openalex.org/W4312924260","https://openalex.org/W4313131769","https://openalex.org/W4319777846","https://openalex.org/W4386390772","https://openalex.org/W4388332081","https://openalex.org/W4388482029","https://openalex.org/W4390195594","https://openalex.org/W4393906056","https://openalex.org/W4399360161","https://openalex.org/W4402327232","https://openalex.org/W4403459022"],"related_works":[],"abstract_inverted_index":{"The":[0,168],"purpose":[1],"of":[2,12,33,56,86,99,116,145,183,197],"the":[3,10,51,106,125,132,138,150,180,184,193,204],"image":[4,14,23,38],"captioning":[5,24],"task":[6],"is":[7,175],"to":[8,22,48,60,78,89,152,162,178],"understand":[9],"content":[11],"an":[13,37],"and":[15,39,81,157],"generate":[16,26,163],"corresponding":[17],"descriptive":[18,27],"text.":[19],"Traditional":[20],"approaches":[21],"typically":[25],"text":[28],"by":[29,119,187],"extracting":[30],"different":[31,54,84,114,143],"types":[32,55,85,115,144],"visual":[34,57,87,117],"features":[35,88,118,147,185],"from":[36,149],"performing":[40],"feature":[41,62,94,155,194],"interactions.":[42,95],"However,":[43],"these":[44],"methods":[45],"often":[46],"fail":[47],"fully":[49,164],"exploit":[50],"interactions":[52,156],"between":[53],"features,":[58,122],"leading":[59],"suboptimal":[61],"integration.":[63],"To":[64],"address":[65],"this":[66],"limitation,":[67],"we":[68,104],"propose":[69],"a":[70],"novel":[71],"Hierarchical":[72,133],"Interaction":[73,134],"Network":[74],"(HIN)":[75],",":[76],"designed":[77,177],"continuously":[79],"extract":[80],"interact":[82],"with":[83],"perform":[90,179],"more":[91],"effective":[92],"multilevel":[93,146,166,181],"Our":[96],"HIN":[97],"consists":[98],"three":[100,120],"key":[101],"modules:":[102],"firstly,":[103],"design":[105],"Cross-Type":[107],"Feature":[108],"Alignment":[109],"(CTFA)":[110],"encoder,":[111],"which":[112,141],"aligns":[113],"global":[121],"so":[123,160],"that":[124,208],"subsequent":[126],"modules":[127],"can":[128],"effectively":[129],"carry":[130,153],"out":[131,154],"(HI)":[135],";":[136],"secondly,":[137],"HI":[139,189],"module,":[140,190],"utilizes":[142],"output":[148],"encoder":[151],"information":[158],"mining,":[159],"as":[161],"mined":[165,186],"features.":[167],"Bottom-up":[169],"Gated":[170],"Attention":[171],"Fusion":[172],"(BGAF)":[173],"decoder":[174],"finally":[176],"decoding":[182],"our":[188,198,209],"further":[191],"enhancing":[192],"interaction":[195],"capabilities":[196],"HIN.":[199],"Moreover,":[200],"additional":[201],"experiments":[202],"on":[203],"MS-COCO":[205],"dataset":[206],"show":[207],"model":[210],"achieves":[211],"new":[212],"state-of-the-art":[213],"performance.":[214],"All":[215],"codes":[216],"are":[217],"available":[218],"at":[219],"https://github.com/songchuanle-1/HIN":[220],".":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
