{"id":"https://openalex.org/W4415537013","doi":"https://doi.org/10.1145/3746027.3755476","title":"Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search","display_name":"Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537013","doi":"https://doi.org/10.1145/3746027.3755476"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755476","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.02340","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031338143","display_name":"Fan Hu","orcid":"https://orcid.org/0000-0002-5371-7780"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Hu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5371-7780","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113398435","display_name":"Zijie Xin","orcid":"https://orcid.org/0000-0002-9220-8735"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Xin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9220-8735","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060270456","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0002-0220-8310"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xirong Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0220-8310","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.25897185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6173","last_page":"6182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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/exploit","display_name":"Exploit","score":0.6855000257492065},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6743000149726868},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6642000079154968},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.611299991607666},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5482000112533569},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.546500027179718},{"id":"https://openalex.org/keywords/multitude","display_name":"Multitude","score":0.46790000796318054},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.451200008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738999724388123},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6855000257492065},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47049999237060547},{"id":"https://openalex.org/C2780565519","wikidata":"https://www.wikidata.org/wiki/Q1208937","display_name":"Multitude","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C147446459","wikidata":"https://www.wikidata.org/wiki/Q11639","display_name":"Dance","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755476","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"},{"id":"pmh:oai:arXiv.org:2508.02340","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02340","pdf_url":"https://arxiv.org/pdf/2508.02340","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.02340","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02340","pdf_url":"https://arxiv.org/pdf/2508.02340","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6518577882","display_name":null,"funder_award_id":"62172420","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2099154756","https://openalex.org/W2148809503","https://openalex.org/W2425121537","https://openalex.org/W2487770199","https://openalex.org/W2950557411","https://openalex.org/W2963703197","https://openalex.org/W2975813532","https://openalex.org/W2980037812","https://openalex.org/W3035356601","https://openalex.org/W3043840704","https://openalex.org/W3155298021","https://openalex.org/W4285606530","https://openalex.org/W4296262844","https://openalex.org/W4312299780","https://openalex.org/W4312777110","https://openalex.org/W4367046992","https://openalex.org/W4386942867","https://openalex.org/W4398147798","https://openalex.org/W4402777374"],"related_works":[],"abstract_inverted_index":{"Ad-hoc":[0],"Video":[1],"Search":[2],"(AVS)":[3],"involves":[4],"using":[5],"a":[6,16,43,46,53,140],"textual":[7],"query":[8,37],"to":[9,64,74,154,202],"search":[10],"for":[11,84,102,118,144],"multiple":[12,90],"relevant":[13,33,76],"videos":[14,77],"in":[15,67],"large":[17],"collection":[18],"of":[19,26,32,42,55,111,158,168,191,196],"unlabeled":[20],"short":[21,117],"videos.":[22,34],"The":[23],"main":[24],"challenge":[25],"AVS":[27,86,185],"is":[28,71],"the":[29,85,100,108,134,156,166,183,189],"visual":[30],"diversity":[31,194],"A":[35],"simple":[36],"such":[38],"as":[39,78,80],"''Find":[40],"shots":[41],"man":[44],"and":[45,61,133,147,150],"woman":[47],"dancing":[48],"together":[49],"indoors''":[50],"can":[51],"span":[52],"multitude":[54],"environments,":[56],"from":[57],"brightly":[58],"lit":[59],"halls":[60],"shadowy":[62],"bars":[63],"dance":[65],"scenes":[66],"black-and-white":[68],"animations.":[69],"It":[70],"therefore":[72],"essential":[73],"retrieve":[75],"comprehensively":[79],"possible.":[81],"Current":[82],"solutions":[83],"task":[87],"primarily":[88],"fuse":[89],"features":[91],"into":[92],"one":[93],"or":[94],"more":[95],"common":[96,122,130,142],"spaces,":[97],"yet":[98],"overlook":[99],"need":[101],"diverse":[103],"spaces.":[104,123,163],"To":[105,164],"fully":[106],"exploit":[107],"expressive":[109],"capability":[110],"individual":[112],"features,":[113],"we":[114,171],"propose":[115],"LPD,":[116],"Learning":[119],"Partially":[120],"Decorrelated":[121],"LPD":[124,138],"incorporates":[125],"two":[126],"key":[127],"innovations:":[128],"feature-specific":[129],"space":[131,143],"construction":[132],"de-correlation":[135,152],"loss.":[136,179],"Specifically,":[137],"learns":[139],"separate":[141],"each":[145],"video":[146],"text":[148],"feature,":[149],"employs":[151],"loss":[153],"diversify":[155],"ordering":[157],"negative":[159],"samples":[160],"across":[161],"different":[162],"enhance":[165,203],"consistency":[167],"multi-space":[169,176],"convergence,":[170],"designed":[172],"an":[173],"entropy-based":[174],"fair":[175],"triplet":[177],"ranking":[178],"Extensive":[180],"experiments":[181],"on":[182],"TRECVID":[184],"benchmarks":[186],"(2016-2023)":[187],"justify":[188],"effectiveness":[190],"LPD.":[192],"Moreover,":[193],"visualizations":[195],"LPD's":[197],"spaces":[198],"highlight":[199],"its":[200],"ability":[201],"result":[204],"diversity.":[205]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}