{"id":"https://openalex.org/W7164826154","doi":"https://doi.org/10.1145/3805622.3810851","title":"SEEDCAP: SEMANTIC EXPANSION AND ENTITY-DRIVEN ZERO-SHOT IMAGE CAPTIONING","display_name":"SEEDCAP: SEMANTIC EXPANSION AND ENTITY-DRIVEN ZERO-SHOT IMAGE CAPTIONING","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164826154","doi":"https://doi.org/10.1145/3805622.3810851"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810851","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810851","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810851","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007028540","display_name":"Binbin Li","orcid":"https://orcid.org/0009-0002-4886-1267"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210159876","display_name":"Institute of Physics","ror":"https://ror.org/05cvf7v30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210159876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China and Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4886-1267","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China and Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210137199","https://openalex.org/I4210159876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057225619","display_name":"Shupei Xiao","orcid":"https://orcid.org/0000-0002-2725-5738"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210159876","display_name":"Institute of Physics","ror":"https://ror.org/05cvf7v30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210159876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shupei Xiao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China and Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5953-2473","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China and Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210137199","https://openalex.org/I4210159876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002436544","display_name":"Dayan Wu","orcid":"https://orcid.org/0000-0002-8604-7226"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dayan Wu","raw_affiliation_strings":["Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8604-7226","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119019893","display_name":"Yang Gengqi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengqi Yang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Biejing, China and Institute of Information Engineering,Chinese Academy of Sciences, Biejing, China"],"raw_orcid":"https://orcid.org/0009-0003-8407-8648","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Biejing, China and Institute of Information Engineering,Chinese Academy of Sciences, Biejing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043232013","display_name":"Siyu Jia","orcid":"https://orcid.org/0009-0003-1631-4602"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Jia","raw_affiliation_strings":["Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-1631-4602","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101604423","display_name":"Zisen Qi","orcid":"https://orcid.org/0009-0008-6340-5749"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zisen Qi","raw_affiliation_strings":["Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6883-6293","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93604706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"826","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9505000114440918,"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":0.9505000114440918,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02710000053048134,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9534000158309937},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7224000096321106},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.578499972820282},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4909999966621399},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4797999858856201},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4514999985694885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3767000138759613},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37070000171661377}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9534000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091999888420105},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7224000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.654699981212616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6269999742507935},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.578499972820282},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810851","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810851","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810851","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810851","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5576708912849426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2185175083","https://openalex.org/W2506483933","https://openalex.org/W2904565150","https://openalex.org/W4288083805","https://openalex.org/W4292828275","https://openalex.org/W4312933868","https://openalex.org/W4312938727","https://openalex.org/W4385567053","https://openalex.org/W4385768038","https://openalex.org/W4386076004","https://openalex.org/W4390873015","https://openalex.org/W4393148638","https://openalex.org/W4393154592","https://openalex.org/W4402703029","https://openalex.org/W4402754015","https://openalex.org/W4403050890","https://openalex.org/W4404782063","https://openalex.org/W4409363063","https://openalex.org/W4413145962","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"image":[1,89],"captioning":[2,68],"(ZIC)":[3],"generates":[4],"natural":[5],"language":[6,139],"descriptions":[7],"for":[8],"images":[9,44,53],"using":[10],"only":[11],"textual":[12,93],"data":[13],"during":[14],"training.":[15],"Recent":[16],"progress":[17],"leverages":[18],"text-to-image":[19],"models":[20,49],"to":[21,141],"construct":[22],"pseudo":[23],"image-text":[24],"pairs,":[25],"alleviating":[26],"the":[27,37,86,108,123],"modality":[28,129],"mismatch":[29],"between":[30,40,88,111],"text-only":[31],"training":[32],"and":[33,42,74,91,98,113,144,160,166],"image-based":[34],"inference.":[35],"However,":[36],"distribution":[38],"gap":[39,110],"synthetic":[41,112],"real":[43,114],"can":[45],"compromise":[46],"performance":[47],"when":[48],"trained":[50],"on":[51,157],"generated":[52],"are":[54,119],"deployed":[55],"in":[56],"real-world":[57],"scenarios.":[58],"To":[59],"address":[60],"this":[61],"challenge,":[62],"we":[63],"propose":[64],"SEEDCap,":[65],"a":[66,76,128,137],"zero-shot":[67,155],"framework":[69],"featuring":[70],"SEED":[71,84],"(Semantic":[72],"Expansion":[73],"Entity-Driven),":[75],"parameter-free":[77],"module":[78],"that":[79,105,151],"performs":[80],"dual-level":[81],"semantic":[82,103],"expansion.":[83],"enhances":[85],"correspondence":[87],"features":[90,118],"retrieved":[92],"cues":[94],"at":[95],"both":[96,158],"entity":[97],"sentence":[99],"levels,":[100],"producing":[101],"enriched":[102],"embeddings":[104],"effectively":[106],"reduce":[107],"distributional":[109],"inputs.":[115],"These":[116],"enhanced":[117],"then":[120],"integrated":[121],"with":[122],"global":[124],"visual":[125],"representation":[126],"through":[127],"fusion":[130],"module,":[131],"which":[132],"is":[133],"subsequently":[134],"decoded":[135],"by":[136],"large":[138],"model":[140],"generate":[142],"accurate":[143],"contextually":[145],"rich":[146],"captions.":[147],"Extensive":[148],"experiments":[149],"demonstrate":[150],"SEEDCap":[152],"achieves":[153],"state-of-the-art":[154],"results":[156],"in-domain":[159],"cross-domain":[161],"benchmarks,":[162],"underscoring":[163],"its":[164],"robustness":[165],"practical":[167],"utility.":[168]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}