{"id":"https://openalex.org/W4415538213","doi":"https://doi.org/10.1145/3746027.3755701","title":"Image Captioning with Multimodal Guidance and Search Space Optimization","display_name":"Image Captioning with Multimodal Guidance and Search Space Optimization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538213","doi":"https://doi.org/10.1145/3746027.3755701"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":"https://openalex.org/A5101333450","display_name":"Yimou Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimou Guo","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-2203-5422","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026770433","display_name":"Yaochen Li","orcid":"https://orcid.org/0000-0001-5741-5280"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaochen Li","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-5741-5280","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000290645","display_name":"Jingze Liu","orcid":"https://orcid.org/0009-0005-3479-9871"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingze Liu","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0005-3479-9871","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103208670","display_name":"Jiahui Feng","orcid":"https://orcid.org/0009-0000-2780-9190"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Feng","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0000-2780-9190","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyi Lou","orcid":"https://orcid.org/0009-0006-7172-3507"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Lou","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0006-7172-3507","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhimin Chen","orcid":"https://orcid.org/0009-0007-8526-7124"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimin Chen","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-8526-7124","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan Gao","orcid":"https://orcid.org/0009-0005-1673-7829"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0005-1673-7829","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082008493","display_name":"Yuanqi Su","orcid":"https://orcid.org/0000-0001-7520-7020"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqi Su","raw_affiliation_strings":["Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7520-7020","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"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":"4982","last_page":"4991"},"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":0.9988999962806702,"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":0.9861000180244446,"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":0.8532000184059143},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6046000123023987},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6013000011444092},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4632999897003174},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42910000681877136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4212000072002411},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8532000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626800000667572},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3319000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2515999972820282},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2506999969482422},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6993940023","display_name":null,"funder_award_id":"62473307,62495084","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W2302086703","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2967957126","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3045623285","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W4282968790","https://openalex.org/W4283793362","https://openalex.org/W4285606316","https://openalex.org/W4293731196","https://openalex.org/W4312289196","https://openalex.org/W4313131769","https://openalex.org/W4382459038","https://openalex.org/W4386076674","https://openalex.org/W4401933296","https://openalex.org/W4406457518"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,60],"bridges":[2],"the":[3,65,89,101,135,157,169,184,196],"gap":[4],"between":[5],"visual":[6,27,66],"perception":[7],"and":[8,31,46,56,77,97,130,151,163,171,198],"natural":[9],"language":[10],"understanding":[11],"by":[12,183,193],"transforming":[13],"image":[14,59],"content":[15],"into":[16],"descriptive":[17],"text.":[18],"While":[19],"existing":[20],"methods":[21],"have":[22],"made":[23],"significant":[24],"progress":[25],"in":[26,37,179],"feature":[28,41,84],"extraction,":[29],"encoding,":[30],"cross-modal":[32,43],"semantic":[33,115],"alignment,":[34],"challenges":[35],"remain":[36],"terms":[38],"of":[39,137,173],"fine-grained":[40],"representation,":[42],"alignment":[44],"efficiency,":[45],"suboptimal":[47],"search":[48,57,158],"strategies.":[49],"To":[50],"address":[51],"these":[52],"issues,":[53],"a":[54,71,81,106,119,144],"multimodal-guided":[55],"space-optimized":[58],"model":[61],"is":[62,123,181],"proposed.":[63],"In":[64,100],"encoding":[67],"stage,":[68,103],"we":[69,104,142],"construct":[70],"hierarchical":[72],"network":[73],"that":[74],"integrates":[75],"regional":[76],"grid":[78],"features":[79],"through":[80],"geometry-constrained":[82],"multi-layer":[83],"aggregation":[85],"mechanism,":[86],"which":[87],"enhances":[88],"model's":[90],"capability":[91],"to":[92,113,125,155],"jointly":[93],"capture":[94],"global":[95],"semantics":[96],"local":[98],"details.":[99],"decoding":[102],"introduce":[105],"dynamic":[107],"grouped":[108],"beam":[109],"width":[110],"adjustment":[111],"strategy":[112],"improve":[114],"path":[116],"exploration.":[117],"Additionally,":[118],"diversity-driven":[120],"scoring":[121],"function":[122],"designed":[124],"enforce":[126],"intra-group":[127],"diversity":[128,172],"rewards":[129],"inter-group":[131],"similarity":[132],"penalties,":[133],"encouraging":[134],"generation":[136],"more":[138],"diverse":[139],"captions.":[140,175],"Finally,":[141],"incorporate":[143],"two-level":[145],"pruning":[146],"algorithm":[147],"based":[148],"on":[149,195],"syntactic":[150],"spatial":[152],"logic":[153],"constraints":[154],"refine":[156],"space":[159],"from":[160],"both":[161,168],"hard":[162],"soft":[164],"constraint":[165],"perspectives,":[166],"improving":[167],"accuracy":[170],"generated":[174],"A":[176],"3%":[177],"improvement":[178],"CIDEr":[180],"achieved":[182],"proposed":[185],"method":[186],"over":[187],"state-of-the-art":[188],"(SOTA)":[189],"models,":[190],"as":[191],"demonstrated":[192],"experiments":[194],"COCO":[197],"Flickr30k":[199],"datasets.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}