{"id":"https://openalex.org/W4387968399","doi":"https://doi.org/10.1145/3581783.3612161","title":"AdaCLIP: Towards Pragmatic Multimodal Video Retrieval","display_name":"AdaCLIP: Towards Pragmatic Multimodal Video Retrieval","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968399","doi":"https://doi.org/10.1145/3581783.3612161"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612161","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612161","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612161","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612161","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102825299","display_name":"Zhiming Hu","orcid":"https://orcid.org/0000-0002-5465-2819"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhiming Hu","raw_affiliation_strings":["Samsung AI Centre Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5465-2819","affiliations":[{"raw_affiliation_string":"Samsung AI Centre Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000229612","display_name":"Angela Ning Ye","orcid":"https://orcid.org/0009-0005-2096-5656"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Angela Ning Ye","raw_affiliation_strings":["Samsung AI Centre Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0005-2096-5656","affiliations":[{"raw_affiliation_string":"Samsung AI Centre Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064063862","display_name":"Salar Hosseini Khorasgani","orcid":"https://orcid.org/0000-0001-6020-3406"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Salar Hosseini Khorasgani","raw_affiliation_strings":["Samsung AI Centre Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6020-3406","affiliations":[{"raw_affiliation_string":"Samsung AI Centre Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025164458","display_name":"Iqbal Mohomed","orcid":"https://orcid.org/0009-0008-0598-8966"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Iqbal Mohomed","raw_affiliation_strings":["Samsung AI Centre Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0008-0598-8966","affiliations":[{"raw_affiliation_string":"Samsung AI Centre Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210123574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102825299"],"corresponding_institution_ids":["https://openalex.org/I4210123574"],"apc_list":null,"apc_paid":null,"fwci":0.942,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77669599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5623","last_page":"5633"},"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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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":0.8892587423324585},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6844848394393921},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.6258189678192139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5279009938240051},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.4482550323009491},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4421408176422119},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.422651469707489},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4167342782020569},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3509249687194824},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10812574625015259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8892587423324585},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6844848394393921},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.6258189678192139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5279009938240051},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4482550323009491},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4421408176422119},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.422651469707489},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4167342782020569},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3509249687194824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10812574625015259},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612161","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612161","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612161","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612161","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612161","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612161","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968399.pdf","grobid_xml":"https://content.openalex.org/works/W4387968399.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2055413877","https://openalex.org/W2108598243","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W2982083293","https://openalex.org/W3043840704","https://openalex.org/W3107788976","https://openalex.org/W3112828033","https://openalex.org/W3168124404","https://openalex.org/W3177017840","https://openalex.org/W3180463990","https://openalex.org/W4214661601","https://openalex.org/W4225414521","https://openalex.org/W4226407477","https://openalex.org/W4290097518","https://openalex.org/W4304014690","https://openalex.org/W4309804076","https://openalex.org/W4312299780","https://openalex.org/W4312364543","https://openalex.org/W4312372711","https://openalex.org/W4312872526","https://openalex.org/W4312999114","https://openalex.org/W4313071966","https://openalex.org/W6600297719","https://openalex.org/W6787247333"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W855007925","https://openalex.org/W2019339419","https://openalex.org/W2618671746","https://openalex.org/W2898107007","https://openalex.org/W1984328213","https://openalex.org/W2119841267"],"abstract_inverted_index":{"Incorporating":[0],"large":[1],"image-text":[2],"foundation":[3],"models":[4],"such":[5,49],"as":[6,50],"CLIP":[7],"has":[8],"substantially":[9],"improved":[10],"the":[11,14,24,31,115,120,135,139,142,164,168,202],"performance":[12,140],"of":[13,63,93,134,141,204],"multimodal":[15,88],"video":[16,28,36,89,112,143,169,198],"retrieval":[17,64,144,199],"task.":[18],"However,":[19],"how":[20],"to":[21,69,99,109,130,151,162,174,189],"practically":[22],"sample":[23,131],"frames":[25,102,136],"from":[26,114],"a":[27,35,81,94,104,126,132,157],"and":[29,67,73,83,103,179],"aggregate":[30,163],"frame":[32,96,106,116,121,165],"features":[33,166],"into":[34,167],"representation":[37],"is":[38],"still":[39],"an":[40,147],"open":[41],"research":[42],"question.":[43],"In":[44,75],"particular,":[45],"real-world":[46],"deployment":[47],"scenarios,":[48],"embodiment":[51],"within":[52],"consumer":[53],"electronics":[54],"or":[55],"cloud-based":[56],"inference":[57],"pipelines,":[58],"require":[59],"two":[60],"key":[61],"facets":[62],"(representation":[65],"building":[66],"search)":[68],"be":[70,152],"computationally":[71],"light":[72],"fast.":[74],"this":[76],"paper,":[77],"we":[78,124,154],"propose":[79,156],"AdaCLIP,":[80],"computation-":[82],"latency-aware":[84],"system":[85],"for":[86],"pragmatic":[87],"retrieval.":[90],"AdaCLIP":[91],"consists":[92],"learning-based":[95],"selection":[97,122],"module":[98,108],"select":[100],"informative":[101],"query-independent":[105,158],"aggregation":[107],"obtain":[110],"strong":[111],"representations":[113],"features.":[117],"Specifically,":[118],"in":[119,146,184],"module,":[123],"introduce":[125],"differentiable":[127],"Hard-Top-k":[128],"algorithm":[129],"subset":[133],"while":[137],"optimizing":[138],"task":[145],"end-to-end":[148],"manner.":[149],"Moreover,":[150],"latency-aware,":[153],"also":[155],"lightweight":[159],"approach,":[160],"MLP-Score,":[161],"representation,":[170],"which":[171],"offers":[172],"up":[173],"142x":[175],"speedup":[176,181],"on":[177,182,195],"GPU":[178],"822x":[180],"CPU":[183],"similarity":[185],"search":[186],"time":[187],"compared":[188],"query-dependent":[190],"matching":[191],"methods.":[192],"Experimental":[193],"results":[194],"several":[196],"popular":[197],"datasets":[200],"confirm":[201],"effectiveness":[203],"AdaCLIP.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}