{"id":"https://openalex.org/W6911688478","doi":"https://doi.org/10.5281/zenodo.14536325","title":"AVCaps: An audio-visual dataset with modality-specific captions","display_name":"AVCaps: An audio-visual dataset with modality-specific captions","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W6911688478","doi":"https://doi.org/10.5281/zenodo.14536325"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14536325","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14536325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14536325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sudarsanam, Parthasaarathy","orcid":"https://orcid.org/0009-0009-3751-6469"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Sudarsanam, Parthasaarathy","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0009-0009-3751-6469","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mart\u00edn Morat\u00f3, Irene","orcid":"https://orcid.org/0000-0002-2115-0193"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mart\u00edn Morat\u00f3, Irene","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-2115-0193","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hakala, Aapo","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Hakala, Aapo","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":null,"display_name":"Virtanen, Tuomas","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Virtanen, Tuomas","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.8974000215530396},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8309999704360962},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5052000284194946},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4287000000476837},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.41940000653266907},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.38749998807907104}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.8974000215530396},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8309999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975999712944031},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14536325","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14536325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14536325","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14536325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,142,163],"AVCaps":[1,101],"dataset":[2,36],"is":[3,102],"an":[4],"audio-visual":[5,92,115,193,197],"captioning":[6],"resource":[7,105],"designed":[8],"to":[9,41,56,69,74],"advance":[10],"research":[11],"in":[12,132,147,167],"multimodal":[13,85,113],"machine":[14],"perception.":[15],"Derived":[16],"from":[17,51,97],"the":[18,35,47,63,78,98,133,185],"VidOR":[19],"dataset,":[20],"it":[21,128],"features":[22],"2061":[23],"video":[24,118,143,180],"clips":[25,144],"spanning":[26],"a":[27,103],"total":[28],"of":[29,137],"28.8":[30],"hours.":[31],"For":[32],"each":[33],"clip,":[34,95],"provides:":[37],"Audio":[38],"Captions:":[39,54,72,89],"Up":[40,55,73],"5":[42,57,75],"textual":[43,58],"captions":[44,59,76,93,164],"describing":[45,77],"only":[46],"audio":[48,80,138,189],"content,":[49,65,83],"crowdsourced":[50,99],"annotators.":[52],"Visual":[53],"focusing":[60],"solely":[61],"on":[62,109],"visual":[64,82,140,191],"annotated":[66],"without":[67],"access":[68],"audio.":[70],"Audio-Visual":[71],"combined":[79,125],"and":[81,117,124,135,139,184,195],"capturing":[84],"interactions.":[86],"GPT-4":[87],"Generated":[88],"Three":[90],"additional":[91],"per":[94],"synthesized":[96],"captions.":[100,198],"valuable":[104],"for":[106],"researchers":[107],"working":[108],"tasks":[110],"such":[111],"as":[112,182],"captioning,":[114],"alignment,":[116],"content":[119],"understanding.":[120],"By":[121],"providing":[122],"separate":[123],"modality-specific":[126],"annotations,":[127],"enables":[129],"fine-grained":[130],"studies":[131],"interaction":[134],"alignment":[136],"modalities.":[141],"are":[145,165],"provided":[146],"three":[148,168],"ZIP":[149],"files:":[150,170],"train_videos.zip:":[151],"1661":[152],"training":[153],"clips.":[154,158,162],"val_videos.zip:":[155],"200":[156,160],"validation":[157],"test_videos.zip:":[159],"testing":[161],"available":[166],"JSON":[169,175],"train_captions.json":[171],"val_captions.json":[172],"test_captions.json":[173],"Each":[174],"file":[176],"contains":[177],"entries":[178],"with":[179],"filenames":[181],"keys,":[183],"corresponding":[186],"values":[187],"include":[188],"captions,":[190,192,194],"LLM-generated":[196]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
