{"id":"https://openalex.org/W7124901247","doi":"https://doi.org/10.1109/cbmi66578.2025.11339348","title":"Dialogue-AV: A Dialogue-Attended Audiovisual Dataset","display_name":"Dialogue-AV: A Dialogue-Attended Audiovisual Dataset","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124901247","doi":"https://doi.org/10.1109/cbmi66578.2025.11339348"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001342472","display_name":"Lu\u00eds Vila\u00e7a","orcid":"https://orcid.org/0000-0002-3640-7019"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Lu\u00eds Vilaca","raw_affiliation_strings":["INESC TEC,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"INESC TEC,Porto,Portugal","institution_ids":["https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009459867","display_name":"Paula Viana","orcid":"https://orcid.org/0000-0001-8447-2360"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paula Viana","raw_affiliation_strings":["INESC TEC,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"INESC TEC,Porto,Portugal","institution_ids":["https://openalex.org/I4210166615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University,Hiroshima,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001342472"],"corresponding_institution_ids":["https://openalex.org/I4210166615"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69962098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904000163078308,"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":0.9904000163078308,"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":0.002099999925121665,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.000699999975040555,"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/benchmarking","display_name":"Benchmarking","score":0.8830999732017517},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7251999974250793},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6449999809265137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.551800012588501},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5454000234603882},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5246999859809875},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4733999967575073}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8830999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791700005531311},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7251999974250793},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6449999809265137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353000164031982},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4733999967575073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43549999594688416},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6605210304260254,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1927052826","https://openalex.org/W2078238240","https://openalex.org/W2185175083","https://openalex.org/W2425121537","https://openalex.org/W2560730294","https://openalex.org/W2765716052","https://openalex.org/W2809191921","https://openalex.org/W2904565150","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W3161945002","https://openalex.org/W3176641147","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W4226289673","https://openalex.org/W4304098310","https://openalex.org/W4312245820","https://openalex.org/W4312380001","https://openalex.org/W4372260310","https://openalex.org/W4385572634","https://openalex.org/W4386065432","https://openalex.org/W4386076615","https://openalex.org/W4387969090","https://openalex.org/W4390871765","https://openalex.org/W4400033239","https://openalex.org/W4403511263"],"related_works":[],"abstract_inverted_index":{"This":[0,32],"work":[1],"introduces":[2],"Dialogue-AV,":[3,127],"a":[4,114,128],"benchmarking":[5,113],"dataset":[6,64,130,149],"for":[7,74,131],"Audio-Video-Language":[8],"(AVL).":[9],"We":[10,96],"propose":[11],"using":[12],"dialogue":[13],"to":[14,36],"describe":[15,93],"video":[16,41],"content":[17],"instead":[18],"of":[19,40,47,112,116,142],"single":[20],"captions,":[21],"capturing":[22],"nuances":[23],"and":[24,29,43,60,135,148],"shared":[25],"meanings":[26],"between":[27],"audio":[28],"visual":[30],"elements.":[31],"approach":[33],"contributes":[34],"significantly":[35],"improving":[37],"the":[38,140],"diversity":[39],"descriptions":[42,73],"enables":[44],"comprehensive":[45],"evaluation":[46],"AVL":[48,133],"learning":[49],"across":[50],"different":[51],"downstream":[52,117],"tasks,":[53],"such":[54],"as":[55],"Cross-Modal":[56],"Retrieval,":[57],"Visual":[58],"Question-Answering,":[59],"Video":[61],"Captioning.":[62],"Our":[63,122],"comprises":[65],"approximately":[66],"258k":[67],"audiovisual":[68],"samples":[69],"accompanied":[70],"by":[71],"dialogue-based":[72,132],"benchmarking.":[75],"Dialogue-AV":[76,109],"builds":[77],"upon":[78],"existing":[79],"State-of-the-Art":[80],"(SOTA)":[81],"datasets":[82],"that":[83,92,108,138],"feature":[84],"human-generated":[85],"descriptions,":[86],"enhancing":[87],"them":[88],"with":[89,119],"model-generated":[90],"ones":[91],"all":[94],"modalities.":[95],"also":[97],"present":[98],"zero-shot":[99],"baseline":[100],"results":[101],"utilising":[102],"SOTA":[103,144],"Visual-Language":[104],"Models":[105],"(VLMs),":[106],"demonstrating":[107],"is":[110],"capable":[111],"variety":[115],"tasks":[118],"diverse":[120],"inputs.":[121],"key":[123],"contributions":[124],"include:":[125],"1)":[126],"benchmark":[129],"models;":[134],"2)":[136],"benchmarks":[137],"expose":[139],"limitations":[141],"current":[143],"VLMs.":[145],"The":[146],"code":[147],"are":[150],"accessible":[151],"at:":[152],"github.com/lvilaca16/dialogue-av.":[153]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-21T00:00:00"}