{"id":"https://openalex.org/W4401936820","doi":"https://doi.org/10.1145/3664524.3675369","title":"Multi Modal Fusion for Video Retrieval based on CLIP Guide Feature Alignment","display_name":"Multi Modal Fusion for Video Retrieval based on CLIP Guide Feature Alignment","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4401936820","doi":"https://doi.org/10.1145/3664524.3675369"},"language":"en","primary_location":{"id":"doi:10.1145/3664524.3675369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664524.3675369","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 2024 ACM ICMR Workshop on Multimodal Video Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664524.3675369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048656618","display_name":"Guanfeng Wu","orcid":"https://orcid.org/0000-0001-8449-974X"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanfeng Wu","raw_affiliation_strings":["School of Mathematics, Southwest Jiaotong University, China","'s , , UK"],"raw_orcid":"https://orcid.org/0000-0001-8449-974X","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]},{"raw_affiliation_string":"'s , , UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037285328","display_name":"Abbas Haider","orcid":"https://orcid.org/0000-0003-1802-3086"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abbas Haider","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK"],"raw_orcid":"https://orcid.org/0000-0003-1802-3086","affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049905270","display_name":"Ivor Spence","orcid":"https://orcid.org/0000-0002-0289-6790"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]},{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Ivor Spence","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","Southwest Jiaotong University Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0289-6790","affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"Southwest Jiaotong University Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460917","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0003-2633-6015"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]},{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","Southwest Jiaotong University Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2633-6015","affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"Southwest Jiaotong University Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"50"},"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":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval 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":0.9994000196456909,"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":0.9986000061035156,"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":0.800627589225769},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.634178102016449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5668748021125793},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5557514429092407},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5113060474395752},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44400155544281006},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3906140923500061}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800627589225769},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.634178102016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5668748021125793},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5557514429092407},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5113060474395752},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44400155544281006},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3906140923500061},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664524.3675369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664524.3675369","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 2024 ACM ICMR Workshop on Multimodal Video Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/f1b82708-8c18-431e-b6d1-d49c4a1fa5f4","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/f1b82708-8c18-431e-b6d1-d49c4a1fa5f4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu , G , Haider , A , Spence , I & Wang , H 2024 , Multi modal fusion for video retrieval based on CLIP guide feature alignment . in MVRMLM '24: Proceedings of 2024 ACM ICMR Workshop on Multimodal Video Retrieval . Proceedings of ACM ICMR Workshop on Multimodal Video Retrieval , Association for Computing Machinery , pp. 45-50 , ICMR '24: International Conference on Multimedia Retrieval Phuket Thailand , Phuket , Thailand , 10/06/2024 . https://doi.org/10.1145/3664524.3675369","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3664524.3675369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664524.3675369","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 2024 ACM ICMR Workshop on Multimodal Video Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6523969021","display_name":"Multimodal Video Search by Examples (MVSE)","funder_award_id":"EP/V002740/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2729738218","https://openalex.org/W2801036749","https://openalex.org/W2981852735","https://openalex.org/W2984008963","https://openalex.org/W3008007823","https://openalex.org/W3013401329","https://openalex.org/W3108009897","https://openalex.org/W3108274592","https://openalex.org/W3135367836","https://openalex.org/W3161997752","https://openalex.org/W3168640669","https://openalex.org/W3204588463","https://openalex.org/W4205248114","https://openalex.org/W4285606530","https://openalex.org/W4286639707","https://openalex.org/W4288089799","https://openalex.org/W4312384316","https://openalex.org/W4312655527","https://openalex.org/W4312938727","https://openalex.org/W4313186260","https://openalex.org/W4386590413","https://openalex.org/W4387168132","https://openalex.org/W4391128821"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2099421762","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2530546662","https://openalex.org/W3147584709","https://openalex.org/W2967030268"],"abstract_inverted_index":{"With":[0],"the":[1,29,35,51,79,85,118],"rise":[2],"of":[3,10,53,87],"short":[4],"video":[5,11,42,54,64,94],"platforms,":[6],"a":[7,45,59,98],"large":[8],"amount":[9],"data":[12,103],"is":[13,44],"generated":[14],"daily.":[15],"These":[16],"videos":[17],"vary":[18],"in":[19,32,50,124],"quality":[20],"and":[21,39,75,82,108],"are":[22,115],"not":[23],"well-tagged.":[24],"How":[25],"to":[26,62,67,117],"fully":[27],"utilize":[28],"multimodal":[30,63,102],"information":[31,77],"videos,":[33],"bridge":[34],"differences":[36],"between":[37],"modalities,":[38],"achieve":[40],"precise":[41],"retrieval":[43],"major":[46],"challenge":[47],"currently":[48],"faced":[49],"field":[52],"retrieval.":[55],"This":[56],"paper":[57],"presents":[58],"novel":[60],"approach":[61],"retrieval,":[65],"aiming":[66],"boost":[68],"search":[69,126],"precision":[70],"by":[71],"incorporating":[72],"visual,":[73],"textual,":[74],"audio":[76],"through":[78,104],"CLIP":[80],"model":[81],"T5.":[83],"Tackling":[84],"issue":[86],"retrieving":[88],"pertinent":[89],"content":[90],"from":[91],"extensive,":[92],"untagged":[93],"repositories,":[95],"we":[96],"propose":[97],"method":[99,112],"that":[100],"fuses":[101],"innovative":[105],"feature":[106],"extraction":[107],"alignment":[109],"techniques.":[110],"Our":[111],"showcases":[113],"performance":[114],"close":[116],"current":[119],"state-of-the-art,":[120],"showcasing":[121],"its":[122],"effectiveness":[123],"improving":[125],"accuracy":[127],"on":[128],"MSR-VTT":[129],"benchmark.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}