{"id":"https://openalex.org/W7117457114","doi":"https://doi.org/10.1109/dicta68720.2025.11302429","title":"Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models","display_name":"Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117457114","doi":"https://doi.org/10.1109/dicta68720.2025.11302429"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302429","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 Digital Image Computing: Techniques and Applications (DICTA)","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/A5100726932","display_name":"Ankit Yadav","orcid":"https://orcid.org/0000-0001-5012-1634"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ankit Yadav","raw_affiliation_strings":["The University of Adelaide,Adelaide,Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121510944","display_name":"Lingqiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["The University of Adelaide,Adelaide,Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["Macquarie University,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"Macquarie University,Sydney,Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100726932"],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66646633,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9591000080108643,"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":0.9591000080108643,"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":0.01140000019222498,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0044999998062849045,"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/generalization","display_name":"Generalization","score":0.569599986076355},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5522000193595886},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.541700005531311},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.3824000060558319},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3763999938964844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092999815940857},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.569599986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5645999908447266},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3824000060558319},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3334999978542328},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302429","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 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6323562264442444,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2264784471","https://openalex.org/W2557169239","https://openalex.org/W2916086000","https://openalex.org/W2963518342","https://openalex.org/W3096609285","https://openalex.org/W3110575265","https://openalex.org/W4226136952","https://openalex.org/W4402670710","https://openalex.org/W4403842540","https://openalex.org/W4405140008"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"the":[3,75,80,156,171],"capabilities":[4],"of":[5,16,158,175],"current":[6],"visionlanguage":[7],"models":[8],"(VLMs)":[9],"in":[10,33,54,124,169],"visual":[11],"understanding":[12],"and":[13,39,50,57,72,101,150,165,173,184],"attribute":[14],"measurement":[15,151],"primitive":[17],"shapes":[18],"using":[19,97],"a":[20],"benchmark":[21],"focused":[22],"on":[23,104,148],"controlled":[24],"<tex":[25,60,186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[26,61,67,69,90,187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2":[27,91],"D$</tex>":[28,189],"shape":[29,40],"configurations":[30],"with":[31,74,127],"variations":[32],"spatial":[34,149,182],"positioning,":[35],"occlusion,":[36],"rotation,":[37,47],"size,":[38],"attributes":[41],"such":[42],"as":[43,52],"type,":[44],"quadrant,":[45],"center-coordinates,":[46],"occlusion":[48],"status,":[49],"color":[51],"shown":[53],"Figure":[55],"1":[56],"supplementary":[58],"Figures":[59,71],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$S":[62],"3":[63],"\\sim":[64,93],"S":[65],"8$</tex><sup":[66],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>All":[70],"Tables":[73],"prefix":[76],"\u2018S\u2019":[77],"refer":[78],"to":[79],"appendix":[81],"materials.":[82],"Code:":[83],"https://github.com/drkkgy/xploring-Primitive-Visual-Measurement.":[84],"We":[85],"fine-tune":[86],"state-of-the-art":[87],"VLMs":[88],"(<tex":[89],"B":[92],"8":[94],"B$</tex>":[95],"parameters)":[96],"Low-Rank":[98],"Adaptation":[99],"(LoRA)":[100],"validate":[102],"them":[103],"multiple":[105],"out-of-domain":[106],"(OD)":[107],"scenarios":[108,126],"from":[109],"our":[110],"proposed":[111],"benchmark.":[112],"Our":[113],"findings":[114],"reveal":[115],"that":[116,134],"coherent":[117],"sentence-based":[118],"outputs":[119],"outperform":[120],"tuple":[121],"formats,":[122],"particularly":[123,177],"OD":[125],"large":[128],"domain":[129],"gaps.":[130],"Additionally,":[131],"we":[132],"demonstrate":[133],"scaling":[135,163],"numeric":[136],"tokens":[137],"during":[138],"loss":[139,162],"computation":[140],"enhances":[141],"numerical":[142],"approximation":[143],"capabilities,":[144],"further":[145],"improving":[146],"performance":[147],"tasks.":[152],"These":[153],"results":[154],"highlight":[155],"importance":[157],"output":[159],"format":[160],"design,":[161],"strategies,":[164],"robust":[166],"generalization":[167],"techniques":[168],"enhancing":[170],"training":[172],"fine-tuning":[174],"VLMs,":[176],"for":[178],"tasks":[179],"requiring":[180],"precise":[181],"approximations":[183],"strong":[185],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$O":[188],"generalization.":[190]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2025-12-29T00:00:00"}