{"id":"https://openalex.org/W4415536769","doi":"https://doi.org/10.1145/3746027.3755445","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","display_name":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536769","doi":"https://doi.org/10.1145/3746027.3755445"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Zhiwei Chen","orcid":"https://orcid.org/0009-0003-0365-8553"},"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":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-0365-8553","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","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":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"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":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-5136-159X","affiliations":[{"raw_affiliation_string":"School of Software, 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":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0007-7724-5662","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030366151","display_name":"Haokun Wen","orcid":"https://orcid.org/0000-0003-0633-3722"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Haokun Wen","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China and School of Data Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-0633-3722","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China and School of Data Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5658-5509","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88101373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6143","last_page":"6152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9969000220298767,"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":0.9965000152587891,"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":0.588699996471405},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5580999851226807},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5311999917030334},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4553999900817871},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.42980000376701355},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42489999532699585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758000135421753},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5688999891281128},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4171000123023987},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.30390000343322754},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29280000925064087}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3236896148","display_name":null,"funder_award_id":"No.:62276155, No.:62476071, No.:U24A20328, No.:624B2047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2798354744","https://openalex.org/W2897628926","https://openalex.org/W2905544595","https://openalex.org/W2956959730","https://openalex.org/W3093002391","https://openalex.org/W3156861396","https://openalex.org/W3157181916","https://openalex.org/W3168433561","https://openalex.org/W3172514680","https://openalex.org/W3174026887","https://openalex.org/W4304080540","https://openalex.org/W4385764644","https://openalex.org/W4386273457","https://openalex.org/W4386501573","https://openalex.org/W4390872636","https://openalex.org/W4396216126","https://openalex.org/W4396642496","https://openalex.org/W4400526206","https://openalex.org/W4401126726","https://openalex.org/W4401500093","https://openalex.org/W4402715906","https://openalex.org/W4403246017","https://openalex.org/W4403791961","https://openalex.org/W4406098393","https://openalex.org/W4408345919","https://openalex.org/W4408354931","https://openalex.org/W4409367947","https://openalex.org/W4410808624","https://openalex.org/W4412876983"],"related_works":[],"abstract_inverted_index":{"Composed":[0,204],"Video":[1],"Retrieval":[2,206],"(CVR)":[3],"is":[4,124,199],"a":[5,16,112],"challenging":[6],"video":[7,18,50,136],"retrieval":[8],"task":[9,32,208],"that":[10,128],"utilizes":[11],"multi-modal":[12,37,47,141],"queries,":[13,48],"consisting":[14],"of":[15,30,97,102],"reference":[17],"and":[19,40,90,137,157,169,182,209,220],"modification":[20,86],"text,":[21],"to":[22,58,81,139,202],"retrieve":[23],"the":[24,36,49,59,68,100,107,117,125,130,184,203],"desired":[25],"target":[26],"video.":[27],"The":[28,223],"core":[29],"this":[31],"lies":[33],"in":[34,70,132],"understanding":[35],"composed":[38,43,192],"query":[39,142],"achieving":[41,190],"accurate":[42],"feature":[44,193],"learning.":[45,194],"Within":[46],"modality":[51],"typically":[52],"carries":[53],"richer":[54],"semantic":[55,94,171],"content":[56],"compared":[57],"textual":[60],"modality.":[61],"However,":[62],"previous":[63],"works":[64],"have":[65],"largely":[66],"overlooked":[67],"disparity":[69,131],"information":[71,133],"density":[72,134],"between":[73,135],"these":[74],"two":[75,82],"modalities.":[76],"This":[77],"limitation":[78],"can":[79],"lead":[80],"critical":[83],"issues:":[84],"1)":[85],"subject":[87],"referring":[88],"ambiguity":[89],"2)":[91],"limited":[92],"detailed":[93,187],"focus,":[95],"both":[96,218],"which":[98],"degrade":[99],"performance":[101,212],"CVR":[103,114,219],"models.":[104],"To":[105],"address":[106],"aforementioned":[108],"issues,":[109],"we":[110],"propose":[111],"novel":[113],"framework,":[115],"namely":[116],"Hierarchical":[118],"Uncertainty-aware":[119],"Disambiguation":[120],"network":[121],"(HUD).":[122],"HUD":[123,177,198],"first":[126],"framework":[127],"leverages":[129],"text":[138],"enhance":[140],"understanding.":[143],"It":[144],"comprises":[145],"three":[146,214],"key":[147],"components:":[148],"(a)":[149],"Holistic":[150],"Pronoun":[151],"Disambiguation,":[152],"(b)":[153],"Atomistic":[154],"Uncertainty":[155],"Modeling,":[156],"(c)":[158],"Holistic-to-Atomistic":[159],"Alignment.":[160],"By":[161],"exploiting":[162],"overlapping":[163],"semantics":[164],"through":[165],"holistic":[166],"cross-modal":[167,175],"interaction":[168],"fine-grained":[170],"alignment":[172],"via":[173],"atomistic-level":[174],"interaction,":[176],"enables":[178],"effective":[179],"object":[180],"disambiguation":[181],"enhances":[183],"focus":[185],"on":[186,227],"semantics,":[188],"thereby":[189],"precise":[191],"Moreover,":[195],"our":[196],"proposed":[197],"also":[200],"applicable":[201],"Image":[205],"(CIR)":[207],"achieves":[210],"state-of-the-art":[211],"across":[213],"benchmark":[215],"datasets":[216],"for":[217],"CIR":[221],"tasks.":[222],"codes":[224],"are":[225],"available":[226],"https://zivchen-ty.github.io/HUD.github.io/.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}