{"id":"https://openalex.org/W4415538266","doi":"https://doi.org/10.1145/3746027.3762039","title":"ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization","display_name":"ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538266","doi":"https://doi.org/10.1145/3746027.3762039"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3762039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762039","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.01259","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104049652","display_name":"Thuan-Phat Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Thinh-Phuc Nguyen","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103941081","display_name":"Thanh-Hai Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thanh-Hai Nguyen","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110814569","display_name":"Ginchev Dinh","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Gia-Huy Dinh","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102587047","display_name":"Lam-Huy Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Lam-Huy Nguyen","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053495766","display_name":"Minh\u2013Triet Tran","orcid":"https://orcid.org/0000-0003-3046-3041"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Triet Tran","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062359795","display_name":"Trung-Nghia Le","orcid":"https://orcid.org/0000-0002-7363-2610"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trung-Nghia Le","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104049652"],"corresponding_institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32397661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14264","last_page":"14270"},"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":0.9955999851226807,"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":0.9902999997138977,"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":0.8377000093460083},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4943000078201294},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4239000082015991},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.423799991607666},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4172999858856201},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39329999685287476},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37369999289512634},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3720000088214874},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.33709999918937683}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8377000093460083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5741000175476074},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5410000085830688},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4553000032901764},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.423799991607666},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4172999858856201},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.26989999413490295},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3762039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762039","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"},{"id":"pmh:oai:arXiv.org:2509.01259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01259","pdf_url":"https://arxiv.org/pdf/2509.01259","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.01259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01259","pdf_url":"https://arxiv.org/pdf/2509.01259","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1989281730","https://openalex.org/W2302086703","https://openalex.org/W2896348597","https://openalex.org/W2963686907","https://openalex.org/W2982573303","https://openalex.org/W3106859150","https://openalex.org/W3137228985","https://openalex.org/W3183226462","https://openalex.org/W4384388099","https://openalex.org/W4396803121","https://openalex.org/W4402703029"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,35],"systems":[2],"often":[3],"produce":[4],"generic":[5,114],"descriptions":[6],"that":[7,36,59,108],"fail":[8],"to":[9,44,133],"capture":[10],"event-level":[11],"semantics":[12],"which":[13],"are":[14],"crucial":[15],"for":[16,30,91,186],"applications":[17],"like":[18],"news":[19],"reporting":[20],"and":[21,34,69,116,120,136],"digital":[22],"archiving.":[23],"We":[24],"present":[25],"ReCap,":[26],"a":[27,78,104,122,157,183],"novel":[28],"pipeline":[29],"event-enriched":[31],"image":[32,188],"retrieval":[33,82],"incorporates":[37],"broader":[38],"contextual":[39],"information":[40,110],"from":[41,111],"relevant":[42],"articles":[43],"generate":[45],"narrative-rich,":[46],"factually":[47],"grounded":[48],"captions.":[49],"Our":[50],"approach":[51],"addresses":[52],"the":[53,140,150,166],"limitations":[54],"of":[55,146,161],"standard":[56],"vision-language":[57],"models":[58],"typically":[60],"focus":[61],"on":[62,139,165],"visible":[63],"content":[64],"while":[65],"missing":[66],"temporal,":[67],"social,":[68],"historical":[70],"contexts.":[71],"ReCap":[72,155],"comprises":[73],"three":[74],"integrated":[75],"components:":[76],"(1)":[77],"robust":[79],"two-stage":[80],"article":[81,112],"system":[83,128],"using":[84],"DINOv2":[85],"embeddings":[86],"with":[87,129,179],"global":[88],"feature":[89],"similarity":[90,101],"initial":[92],"candidate":[93],"selection":[94],"followed":[95],"by":[96],"patch-level":[97],"mutual":[98],"nearest":[99],"neighbor":[100],"re-ranking;":[102],"(2)":[103],"context":[105],"extraction":[106],"framework":[107],"synthesizes":[109],"summaries,":[113],"captions,":[115],"original":[117],"source":[118],"metadata;":[119],"(3)":[121],"large":[123],"language":[124],"model-based":[125],"caption":[126],"generation":[127],"Semantic":[130],"Gaussian":[131],"Normalization":[132],"enhance":[134],"fluency":[135],"relevance.":[137],"Evaluated":[138],"OpenEvents":[141],"V1":[142],"dataset":[143],"as":[144],"part":[145],"Track":[147],"1":[148],"in":[149,175,190],"EVENTA":[151],"2025":[152],"Grand":[153],"Challenge,":[154],"achieved":[156],"strong":[158],"overall":[159],"score":[160],"0.54666,":[162],"ranking":[163],"2nd":[164],"private":[167],"test":[168],"set.":[169],"These":[170],"results":[171],"highlight":[172],"ReCap's":[173],"effectiveness":[174],"bridging":[176],"visual":[177],"perception":[178],"real-world":[180],"knowledge,":[181],"offering":[182],"practical":[184],"solution":[185],"context-aware":[187],"understanding":[189],"high-stakes":[191],"domains.":[192],"The":[193],"code":[194],"is":[195],"available":[196],"at":[197],"https://github.com/Noridom1/EVENTA2025-Event-Enriched-Image-Captioning.":[198]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}