{"id":"https://openalex.org/W7161117988","doi":"https://doi.org/10.1145/3746467.3801518","title":"Visual Linguistics of Memorability: A Caption-Based Framework for Image Memorability Analysis","display_name":"Visual Linguistics of Memorability: A Caption-Based Framework for Image Memorability Analysis","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7161117988","doi":"https://doi.org/10.1145/3746467.3801518"},"language":null,"primary_location":{"id":"doi:10.1145/3746467.3801518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801518","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 ACM Southeast Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746467.3801518","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136187506","display_name":"Sai Radhika Koneru","orcid":"https://orcid.org/0009-0003-3797-2735"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sai Radhika Koneru","raw_affiliation_strings":["University of North Carolina at Charlotte, Charlotte, NC, USA"],"raw_orcid":"https://orcid.org/0009-0003-3797-2735","affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte, Charlotte, NC, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024732821","display_name":"Laurel Powell","orcid":"https://orcid.org/0000-0002-4445-4405"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurel Boykin Powell","raw_affiliation_strings":["Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA"],"raw_orcid":"https://orcid.org/0000-0002-4445-4405","affiliations":[{"raw_affiliation_string":"Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5136187506"],"corresponding_institution_ids":["https://openalex.org/I102149020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9419527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.88919997215271,"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":0.88919997215271,"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":0.026000000536441803,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.01590000092983246,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5586000084877014},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5196999907493591},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4397999942302704},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.3797000050544739},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3580000102519989},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722000002861023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6549999713897705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C26983874","wikidata":"https://www.wikidata.org/wiki/Q263864","display_name":"Tag cloud","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746467.3801518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801518","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 ACM Southeast Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746467.3801518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801518","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 ACM Southeast Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6305097341537476,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2009627211","https://openalex.org/W2011301426","https://openalex.org/W2018286305","https://openalex.org/W2022872918","https://openalex.org/W2142978433","https://openalex.org/W2203368333","https://openalex.org/W2288014083","https://openalex.org/W2997591727","https://openalex.org/W3098768325","https://openalex.org/W3150635270","https://openalex.org/W3210920396"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,20],"framework":[4],"for":[5],"understanding":[6],"image":[7,25,81],"memorability":[8],"through":[9],"textual":[10],"captions":[11,65],"derived":[12],"from":[13,55],"the":[14],"LaMem":[15],"dataset.":[16],"We":[17,51],"utilize":[18],"BLIP,":[19],"vision-language":[21],"model,":[22],"to":[23],"generate":[24],"captions,":[26],"which":[27],"are":[28,39,66,77],"subsequently":[29],"processed":[30],"and":[31,35,42,58,85],"embedded":[32],"using":[33,44],"Doc2Vec":[34],"Word2Vec.":[36],"Memorability":[37],"scores":[38],"discretized,":[40],"clustered,":[41],"classified":[43],"stratified":[45],"K-fold":[46],"validation":[47],"across":[48],"multiple":[49],"models.":[50,88],"present":[52],"qualitative":[53],"insights":[54],"word":[56],"clouds":[57],"cluster":[59],"analyses,":[60],"indicating":[61],"that":[62,74],"semantically":[63],"rich":[64],"linked":[67],"with":[68],"high":[69],"memorability.":[70],"Our":[71],"findings":[72],"suggest":[73],"linguistic":[75],"features":[76],"viable":[78],"predictors":[79],"of":[80],"memorability,":[82],"supporting":[83],"interpretable":[84],"cognitively":[86],"aligned":[87]},"counts_by_year":[],"updated_date":"2026-05-15T06:12:33.780692","created_date":"2026-05-15T00:00:00"}