{"id":"https://openalex.org/W7165466758","doi":"https://doi.org/10.1016/j.jvcir.2026.104879","title":"CapVA: Towards hierarchical understanding in Text\u2013Video Retrieval With Caption as Video Assistant","display_name":"CapVA: Towards hierarchical understanding in Text\u2013Video Retrieval With Caption as Video Assistant","publication_year":2026,"publication_date":"2026-06-20","ids":{"openalex":"https://openalex.org/W7165466758","doi":"https://doi.org/10.1016/j.jvcir.2026.104879"},"language":"en","primary_location":{"id":"doi:10.1016/j.jvcir.2026.104879","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104879","pdf_url":null,"source":{"id":"https://openalex.org/S105424869","display_name":"Journal of Visual Communication and Image Representation","issn_l":"1047-3203","issn":["1047-3203","1095-9076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Visual Communication and Image Representation","raw_type":"journal-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/A5022345139","display_name":"Zhipeng Yu","orcid":"https://orcid.org/0000-0003-1132-859X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhipeng Yu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1132-859X","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053213796","display_name":"Yangbangyan Jiang","orcid":"https://orcid.org/0000-0002-0148-8306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangbangyan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139028316","display_name":"Qianqian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianqian Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2150,"currency":"USD","value_usd":2150},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8049921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"119","issue":null,"first_page":"104879","last_page":"104879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8287000060081482,"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":0.8287000060081482,"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":0.11169999837875366,"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/T12031","display_name":"Speech and dialogue systems","score":0.01080000028014183,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/closed-captioning","display_name":"Closed captioning","score":0.3386000096797943},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.3287000060081482},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2551000118255615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4016000032424927},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.jvcir.2026.104879","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104879","pdf_url":null,"source":{"id":"https://openalex.org/S105424869","display_name":"Journal of Visual Communication and Image Representation","issn_l":"1047-3203","issn":["1047-3203","1095-9076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Visual Communication and Image Representation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2885775891","https://openalex.org/W2914699769","https://openalex.org/W2956959730","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3154280800","https://openalex.org/W3168640669","https://openalex.org/W3204588463","https://openalex.org/W4236329806","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312614039","https://openalex.org/W4312938727","https://openalex.org/W4386065852","https://openalex.org/W4386072365","https://openalex.org/W4386076265","https://openalex.org/W4387968456","https://openalex.org/W4387968589","https://openalex.org/W4390872434","https://openalex.org/W4390874542","https://openalex.org/W4390874668","https://openalex.org/W4390889802","https://openalex.org/W4392904725","https://openalex.org/W4393159202","https://openalex.org/W4402704596","https://openalex.org/W4402980118","https://openalex.org/W4403791593","https://openalex.org/W4403889113","https://openalex.org/W7133193597","https://openalex.org/W7133204608","https://openalex.org/W7133218155"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-30T06:16:30.551410","created_date":"2026-06-21T00:00:00"}
