{"id":"https://openalex.org/W4406459110","doi":"https://doi.org/10.1109/bigdata62323.2024.10825297","title":"Beyond Essentials: Nuanced and Diverse Text-to-video Retrieval","display_name":"Beyond Essentials: Nuanced and Diverse Text-to-video Retrieval","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459110","doi":"https://doi.org/10.1109/bigdata62323.2024.10825297"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/247246","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102025383","display_name":"Yuchen Yang","orcid":"https://orcid.org/0000-0002-6866-1409"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Yuchen Yang","raw_affiliation_strings":["EPFL,Laboratory of Experimental Museology,Lausanne,Switzerland"],"affiliations":[{"raw_affiliation_string":"EPFL,Laboratory of Experimental Museology,Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102025383"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26626814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2549","last_page":"2557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9994999766349792,"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":0.9915000200271606,"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":0.7306045889854431},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5737894177436829},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.5246567726135254},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42594659328460693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33814990520477295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306045889854431},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5737894177436829},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.5246567726135254},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42594659328460693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33814990520477295}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/247246","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/247246","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/247246","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/247246","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1989601496","https://openalex.org/W2105809105","https://openalex.org/W2317193121","https://openalex.org/W2318497026","https://openalex.org/W2425121537","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2954841306","https://openalex.org/W2965458216","https://openalex.org/W2984008963","https://openalex.org/W3043840704","https://openalex.org/W3094502228","https://openalex.org/W3119221111","https://openalex.org/W3126721948","https://openalex.org/W3130796238","https://openalex.org/W3156892778","https://openalex.org/W3158657276","https://openalex.org/W3172655693","https://openalex.org/W3174873881","https://openalex.org/W3176799298","https://openalex.org/W3180463990","https://openalex.org/W3196974791","https://openalex.org/W4206094475","https://openalex.org/W4211053420","https://openalex.org/W4221163941","https://openalex.org/W4285606530","https://openalex.org/W4295312788","https://openalex.org/W4297808394","https://openalex.org/W4307129979","https://openalex.org/W4312372711","https://openalex.org/W4312384316","https://openalex.org/W4312661097","https://openalex.org/W4321614506","https://openalex.org/W4378942464","https://openalex.org/W4384392955","https://openalex.org/W4386072365","https://openalex.org/W4387496073","https://openalex.org/W4390873165","https://openalex.org/W4399655895","https://openalex.org/W4403511263","https://openalex.org/W4404724811","https://openalex.org/W6631190155","https://openalex.org/W6750041603","https://openalex.org/W6766582784","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6791353385","https://openalex.org/W6797148833","https://openalex.org/W6809975043","https://openalex.org/W6844194202","https://openalex.org/W6847363464","https://openalex.org/W6851997505","https://openalex.org/W6853320480","https://openalex.org/W6854451932","https://openalex.org/W6870122244"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3204019825","https://openalex.org/W2333966947","https://openalex.org/W2399947890"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,11,177],"text-to-video":[3,71],"retrieval":[4,31,72],"has":[5],"advanced":[6],"significantly":[7],"with":[8,116,195],"the":[9,97,112,174],"evolution":[10],"language":[12],"models":[13,147,197,205],"and":[14,27,67,93,108,134,159],"large-scale":[15],"pre-training":[16],"on":[17,25,34,88,151,198],"generated":[18],"caption-video":[19],"pairs.":[20],"Current":[21],"methods":[22],"predominantly":[23],"focus":[24],"visual":[26,107,158],"event-based":[28,160],"details,":[29],"making":[30],"largely":[32],"reliant":[33],"tangible":[35],"aspects.":[36],"However,":[37],"videos":[38],"encompass":[39],"more":[40,163,208],"than":[41],"just":[42],"\"seen\"":[43],"or":[44],"\"heard\"":[45],"elements,":[46],"containing":[47],"diverse,":[48],"nuanced":[49,175],"layers":[50],"that":[51,63,154,172],"are":[52,148],"often":[53,149],"overlooked.This":[54],"work":[55],"addresses":[56],"this":[57,117,214],"gap":[58],"by":[59,213],"introducing":[60],"a":[61,89,101,182],"method":[62,192],"incorporates":[64],"audio,":[65,91],"style,":[66,92],"emotion":[68],"considerations":[69],"into":[70],"through":[73],"three":[74],"key":[75],"components.":[76],"First,":[77],"an":[78],"augmentation":[79],"block":[80,105],"is":[81,125],"implemented":[82],"to":[83,131],"generate":[84],"additional":[85],"textual":[86,119,133],"information":[87,143],"video\u2019s":[90],"emotional":[94],"aspects,":[95],"supplementing":[96],"original":[98],"caption.":[99],"Second,":[100],"cross-modal":[102],"audiovisual":[103],"attention":[104],"fuses":[106],"audio":[109],"data":[110],"within":[111],"video,":[113],"aligning":[114],"it":[115,202],"enriched":[118],"information.":[120],"Third,":[121],"hybrid":[122],"space":[123],"learning":[124],"applied,":[126],"using":[127],"multiple":[128],"latent":[129],"spaces":[130],"align":[132],"video":[135,178],"data,":[136],"which":[137],"minimizes":[138],"potential":[139],"conflicts":[140],"between":[141],"various":[142],"sources.In":[144],"standard":[145],"evaluations,":[146],"tested":[150],"benchmark":[152],"datasets":[153],"emphasize":[155],"simple,":[156],"short,":[157],"queries.":[161],"To":[162],"accurately":[164],"assess":[165],"model":[166],"performance":[167],"under":[168],"diverse":[169],"query":[170],"conditions":[171],"capture":[173],"dimensions":[176],"content,":[179],"we":[180],"developed":[181],"new":[183],"evaluation":[184],"dataset.":[185,217],"Our":[186],"results":[187],"demonstrate":[188],"that,":[189],"while":[190],"our":[191],"performs":[193],"comparably":[194],"state-of-the-art":[196],"conventional":[199],"test":[200,216],"sets,":[201],"surpasses":[203],"non-pre-trained":[204],"when":[206],"addressing":[207],"complex":[209],"queries,":[210],"as":[211],"evidenced":[212],"novel":[215]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}