{"id":"https://openalex.org/W4396218624","doi":"https://doi.org/10.1145/3641019","title":"The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model","display_name":"The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4396218624","doi":"https://doi.org/10.1145/3641019"},"language":"en","primary_location":{"id":"doi:10.1145/3641019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641019","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-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/A5051941811","display_name":"Yilin Ye","orcid":"https://orcid.org/0000-0001-8874-5928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilin Ye","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8874-5928","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037866250","display_name":"Qian Zhu","orcid":"https://orcid.org/0000-0001-5108-3414"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qian Zhu","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-5108-3414","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075939839","display_name":"Shishi Xiao","orcid":"https://orcid.org/0009-0008-0262-5289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shishi Xiao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-0262-5289","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432244","display_name":"Kang Zhang","orcid":"https://orcid.org/0000-0003-3802-7535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3802-7535","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100660205","display_name":"Wei Zeng","orcid":"https://orcid.org/0000-0002-5600-8824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zeng","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5600-8824","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2481,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88858343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"8","issue":"CSCW1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998000264167786,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.5595803260803223},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5423427820205688},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5416666865348816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4138229489326477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5595803260803223},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5423427820205688},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5416666865348816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4138229489326477}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3641019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641019","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-137408","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-137408","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W19399978","https://openalex.org/W1510632636","https://openalex.org/W2011143967","https://openalex.org/W2096733369","https://openalex.org/W2105481243","https://openalex.org/W2118322263","https://openalex.org/W2118597426","https://openalex.org/W2121548608","https://openalex.org/W2124332348","https://openalex.org/W2126448884","https://openalex.org/W2127586137","https://openalex.org/W2153404544","https://openalex.org/W2471768434","https://openalex.org/W2590822507","https://openalex.org/W2610551042","https://openalex.org/W2898076813","https://openalex.org/W2905544595","https://openalex.org/W2914393402","https://openalex.org/W2915038596","https://openalex.org/W2942422815","https://openalex.org/W2962964995","https://openalex.org/W2967819436","https://openalex.org/W2985406956","https://openalex.org/W2988281744","https://openalex.org/W2994818707","https://openalex.org/W3035454331","https://openalex.org/W3043859333","https://openalex.org/W3108274592","https://openalex.org/W3153469116","https://openalex.org/W4212975704","https://openalex.org/W4220664175","https://openalex.org/W4286611322","https://openalex.org/W4297461125","https://openalex.org/W4312825288","https://openalex.org/W4312933868","https://openalex.org/W4321472415","https://openalex.org/W4385572867","https://openalex.org/W4386076215","https://openalex.org/W4390874575","https://openalex.org/W6600234944","https://openalex.org/W6601613822"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"search":[1,18,47,55,139,168,177,187,193,217,233,244],"is":[2],"an":[3,59,117,185],"essential":[4],"and":[5,72,81,129,194,203,222,237],"user-friendly":[6],"method":[7],"to":[8,70,77,102,121,161,170,199,230],"explore":[9],"vast":[10],"galleries":[11],"of":[12,53,106],"digital":[13],"images.":[14],"However,":[15],"existing":[16],"image":[17,29,46,186,216],"methods":[19],"heavily":[20],"rely":[21],"on":[22],"proximity":[23],"measurements":[24],"like":[25],"tag":[26],"matching":[27],"or":[28,173],"similarity,":[30],"requiring":[31],"precise":[32],"user":[33,61,75,138,197],"inputs":[34,76],"for":[35,43,146,189],"satisfactory":[36],"results.":[37,83],"To":[38],"meet":[39],"the":[40,104,155,167,182,210,220],"growing":[41],"demand":[42],"a":[44,89,94,111,131,142,196,240],"contemporary":[45],"engine":[48],"that":[49,92,115,135,209],"enables":[50,159],"accurate":[51,80],"comprehension":[52,105],"users'":[54,215],"intentions,":[56],"we":[57],"introduce":[58],"innovative":[60],"intent":[62,156],"expansion":[63,157],"framework.":[64],"Our":[65],"framework":[66,158,183,212],"leverages":[67],"visual-language":[68],"models":[69,101],"parse":[71],"compose":[73],"multi-modal":[74],"provide":[78],"more":[79,147,235,241],"satisfying":[82],"It":[84],"comprises":[85],"two-stage":[86],"processes:":[87],"1)":[88],"parsing":[90,96,113,221],"stage":[91,134],"incorporates":[93],"language":[95,100],"module":[97,114,120],"with":[98,110,166],"large":[99],"enhance":[103],"textual":[107],"inputs,":[108],"along":[109],"visual":[112,125],"integrates":[116],"interactive":[118],"segmentation":[119],"swiftly":[122],"identify":[123],"detailed":[124,176],"elements":[126],"within":[127],"images;":[128],"2)":[130],"logic":[132,144],"composition":[133],"combines":[136],"multiple":[137],"intents":[140,178,234],"into":[141,184],"unified":[143],"expression":[145],"sophisticated":[148],"operations":[149],"in":[150,227,239],"complex":[151],"searching":[152],"scenarios.":[153],"Moreover,":[154],"users":[160,229],"perform":[162],"flexible":[163],"contextualized":[164,223],"interactions":[165,224],"results":[169,207],"further":[171],"specify":[172],"adjust":[174],"their":[175,232],"iteratively.":[179],"We":[180],"implemented":[181],"system":[188],"NFT":[190],"(non-fungible":[191],"token)":[192],"conducted":[195],"study":[198],"evaluate":[200],"its":[201],"usability":[202],"novel":[204],"properties.":[205],"The":[206],"indicate":[208],"proposed":[211],"significantly":[213],"improves":[214],"experience.":[218,245],"Particularly":[219],"prove":[225],"useful":[226],"allowing":[228],"express":[231],"accurately":[236],"engage":[238],"enjoyable":[242],"iterative":[243]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}