{"id":"https://openalex.org/W7125135848","doi":"https://doi.org/10.1109/cbmi66578.2025.11339266","title":"Exploring the Effect of Size, Architecture and Fine-Tuning Hyperparameters on Large Visual-Language Model Adaptation for Video Memorability Prediction","display_name":"Exploring the Effect of Size, Architecture and Fine-Tuning Hyperparameters on Large Visual-Language Model Adaptation for Video Memorability Prediction","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7125135848","doi":"https://doi.org/10.1109/cbmi66578.2025.11339266"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-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/A5123498422","display_name":"David Luna-Garc\u00eda","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"David Luna-Garc\u00eda","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093620465","display_name":"Iv\u00e1n Mart\u00edn-Fern\u00e1ndez","orcid":"https://orcid.org/0009-0004-2769-9752"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Iv\u00e1n Mart\u00edn-Fern\u00e1ndez","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094034370","display_name":"Sergio Esteban-Romero","orcid":"https://orcid.org/0009-0008-6336-7877"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergio Esteban-Romero","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058484271","display_name":"Manuel Gil-Mart\u00edn","orcid":"https://orcid.org/0000-0002-4285-6224"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel Gil-Mart\u00edn","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032875587","display_name":"Fernando Fern\u00e1ndez-Mart\u00ednez","orcid":"https://orcid.org/0000-0003-3877-0089"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Fern\u00e1ndez-Mart\u00ednez","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica de Madrid,THAU Group, IPTC,Madrid,Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5123498422"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67537401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6227999925613403,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6227999925613403,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2506999969482422,"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":0.017999999225139618,"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/adaptation","display_name":"Adaptation (eye)","score":0.7458999752998352},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7168999910354614},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.36629998683929443},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3287000060081482},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.31290000677108765},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.29159998893737793},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2865999937057495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021000027656555},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7458999752998352},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7168999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115999817848206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5644999742507935},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8337827324867249}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322138","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2158155099","https://openalex.org/W2560730294","https://openalex.org/W2807844012","https://openalex.org/W2963563276","https://openalex.org/W3039448085","https://openalex.org/W3161118112","https://openalex.org/W4390446690","https://openalex.org/W4400125901","https://openalex.org/W4408167660","https://openalex.org/W4413286666"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"video":[1],"memorability":[2],"involves":[3],"modeling":[4],"audiovisual":[5],"content":[6],"to":[7,38],"estimate":[8],"its":[9],"likelihood":[10],"of":[11,25,45,65,83,120],"being":[12],"remembered-relevant":[13],"in":[14,114],"areas":[15],"like":[16],"recommendation,":[17],"marketing,":[18],"and":[19,51,79,116],"education.":[20],"Leveraging":[21],"the":[22,43,68,81,87,90,97,118],"semantic":[23],"power":[24],"Large":[26],"Vision-Language":[27],"Models":[28],"(LVLMs),":[29],"we":[30],"adapt":[31],"Qwen2.5-VL":[32],"models":[33],"using":[34,72],"Low-Rank":[35],"Adaptation":[36],"(LoRA)":[37],"this":[39],"task.":[40],"We":[41],"evaluate":[42],"influence":[44],"model":[46,88],"size":[47],"(3B":[48],"vs.":[49],"7B)":[50],"LoRA":[52],"hyperparameters":[53],"(<tex":[54],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$r$</tex>,":[56],"\u03b1)":[57],"on":[58,67],"performance.":[59],"Our":[60],"best":[61,91],"result,":[62],"an":[63],"SRCC":[64],"0.7658":[66],"Memento10k":[69],"development":[70],"dataset":[71],"5-Fold":[73],"Cross":[74],"Validation,":[75],"surpasses":[76],"previous":[77],"approaches":[78],"confirms":[80],"importance":[82],"careful":[84],"tuning.":[85],"Notably,":[86],"with":[89],"zero-shot":[92,103],"performance":[93],"(3B)":[94],"also":[95],"achieved":[96],"highest":[98],"fine-tuned":[99],"score,":[100],"showing":[101],"that":[102],"evaluation":[104],"can":[105],"predict":[106],"adaptation":[107],"success.":[108],"Results":[109],"challenge":[110],"assumptions":[111],"about":[112],"scaling":[113],"LVLMs":[115],"highlight":[117],"potential":[119],"smaller,":[121],"well-adapted":[122],"models.":[123]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-22T00:00:00"}