{"id":"https://openalex.org/W7164828144","doi":"https://doi.org/10.1145/3805622.3810601","title":"IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval","display_name":"IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164828144","doi":"https://doi.org/10.1145/3805622.3810601"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810601","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 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810601","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129731238","display_name":"Jiale Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Huang","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0002-9435-4127","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136792084","display_name":"Zixu Li","orcid":"https://orcid.org/0009-0001-5136-159X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixu Li","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-5136-159X","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125059455","display_name":"Z Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Chen","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-0365-8553","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050782735","display_name":"Zhiheng Fu","orcid":"https://orcid.org/0009-0007-7724-5662"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Fu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0007-7724-5662","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092465011","display_name":"Chunxiao Wang","orcid":"https://orcid.org/0009-0000-6617-0924"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxiao Wang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0009-0000-6617-0924","affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101875643","display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":["Shandong Unversity, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"Shandong Unversity, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93619838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9584000110626221,"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":0.9584000110626221,"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":0.020600000396370888,"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":0.005400000140070915,"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/semantics","display_name":"Semantics (computer science)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.48570001125335693},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.46889999508857727},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4684000015258789},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4357999861240387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4142000079154968},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.30970001220703125},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.3034000098705292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267999887466431},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4999000132083893},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.48570001125335693},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.30970001220703125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.27070000767707825},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810601","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 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810601","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 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2544587078","https://openalex.org/W2798794842","https://openalex.org/W3002678554","https://openalex.org/W3092962760","https://openalex.org/W3157181916","https://openalex.org/W3174026887","https://openalex.org/W3203247393","https://openalex.org/W3206012133","https://openalex.org/W4224929299","https://openalex.org/W4295308727","https://openalex.org/W4312472480","https://openalex.org/W4375801803","https://openalex.org/W4382461147","https://openalex.org/W4385572711","https://openalex.org/W4386075952","https://openalex.org/W4386273457","https://openalex.org/W4386501573","https://openalex.org/W4386527955","https://openalex.org/W4387968356","https://openalex.org/W4390203954","https://openalex.org/W4390872636","https://openalex.org/W4396594821","https://openalex.org/W4400530983","https://openalex.org/W4402673375","https://openalex.org/W4402715906","https://openalex.org/W4402726939","https://openalex.org/W4402754243","https://openalex.org/W4403246017","https://openalex.org/W4403791316","https://openalex.org/W4403791324","https://openalex.org/W4403791707","https://openalex.org/W4404781091","https://openalex.org/W4408345919","https://openalex.org/W4408354931","https://openalex.org/W4409347665","https://openalex.org/W4409367947","https://openalex.org/W4412945336","https://openalex.org/W4413145898","https://openalex.org/W4413147218","https://openalex.org/W4415536769","https://openalex.org/W4415538366","https://openalex.org/W4415797492","https://openalex.org/W4416183038","https://openalex.org/W4417400953","https://openalex.org/W7137960719","https://openalex.org/W7138107458","https://openalex.org/W7138232037","https://openalex.org/W7138238529","https://openalex.org/W7140086938","https://openalex.org/W7140557520","https://openalex.org/W7155092706","https://openalex.org/W7160118679"],"related_works":[],"abstract_inverted_index":{"Composed":[0,141],"Video":[1],"Retrieval":[2,143],"(CVR)":[3],"is":[4],"designed":[5],"to":[6,108],"retrieve":[7],"a":[8,13,18],"target":[9],"video":[10,15],"that":[11],"matches":[12],"reference":[14],"modified":[16,30],"by":[17],"modification":[19,37],"text.":[20],"While":[21],"existing":[22],"methods":[23],"explore":[24],"cross-modal":[25],"correspondences,":[26],"they":[27],"often":[28],"assume":[29],"objects":[31],"appear":[32],"directly":[33],"in":[34,137],"videos.":[35],"However,":[36],"texts":[38],"frequently":[39],"describe":[40],"concepts":[41,107],"not":[42],"explicitly":[43],"presented":[44],"but":[45],"implicitly":[46],"expressed":[47],"through":[48],"semantically":[49],"related":[50],"visual":[51,111,127],"cues":[52],"(e.g.,":[53],"\u201ccake\u201d":[54],"implying":[55],"\u201cbirthday":[56],"party\u201d).":[57],"Current":[58],"approaches":[59],"typically":[60],"rely":[61],"on":[62],"aligning":[63],"explicit":[64,89,126],"feature":[65],"representations":[66],"within":[67],"the":[68,118,123],"concrete":[69],"space,":[70],"neglecting":[71],"critical":[72],"latent":[73,106],"associations.":[74],"To":[75],"address":[76],"this,":[77],"we":[78],"propose":[79],"an":[80],"adaptIve":[81],"scheMa-ImAGery":[82],"enhanced":[83],"composItional":[84],"NEtwork":[85],"(IMAGINE).":[86],"Unlike":[87],"standard":[88],"matching,":[90],"IMAGINE":[91,133],"materializes":[92],"implicit":[93,115,130],"semantics":[94],"(termed":[95],"schema":[96],"imagery)":[97],"via":[98],"dynamic":[99],"multimodal":[100],"prototypes.":[101],"These":[102],"prototypes":[103],"capture":[104],"shared":[105],"adaptively":[109],"modulate":[110],"features,":[112],"effectively":[113],"injecting":[114],"guidance":[116],"into":[117],"retrieval":[119,131],"process.":[120],"By":[121],"bridging":[122],"gap":[124],"between":[125],"contents":[128],"and":[129,140],"intentions,":[132],"achieves":[134],"state-of-the-art":[135],"performance":[136],"both":[138],"CVR":[139],"Image":[142],"(CIR)":[144],"across":[145],"three":[146],"widely":[147],"used":[148],"benchmarks.":[149]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}