{"id":"https://openalex.org/W7166665977","doi":"https://doi.org/10.1016/j.jvcir.2026.104886","title":"MotionViLA: A motion-aware video understanding model for video localization and question answering","display_name":"MotionViLA: A motion-aware video understanding model for video localization and question answering","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166665977","doi":"https://doi.org/10.1016/j.jvcir.2026.104886"},"language":"en","primary_location":{"id":"doi:10.1016/j.jvcir.2026.104886","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104886","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/A5101333432","display_name":"Zehua Ji","orcid":"https://orcid.org/0000-0003-1999-4335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehua Ji","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1999-4335","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109299440","display_name":"Weifeng Lv","orcid":"https://orcid.org/0000-0002-7061-9509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weifeng Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043477487","display_name":"Junlin Hu","orcid":"https://orcid.org/0000-0002-0117-3494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junlin Hu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0117-3494","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139710320","display_name":"Chao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139676659","display_name":"Zekun Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zekun Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139697199","display_name":"Jian Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Huang","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":0.85558104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"119","issue":null,"first_page":"104886","last_page":"104886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9660000205039978,"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":0.9660000205039978,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.004000000189989805,"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/question-answering","display_name":"Question answering","score":0.7379000186920166},{"id":"https://openalex.org/keywords/online-video","display_name":"Online video","score":0.4239000082015991},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.3686000108718872},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.29179999232292175},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.26030001044273376}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7379000186920166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.jvcir.2026.104886","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104886","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":[{"id":"https://openalex.org/F4320335774","display_name":"Key Technologies Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2963341956","https://openalex.org/W3197457832","https://openalex.org/W4313071966","https://openalex.org/W4383112678","https://openalex.org/W4386071468","https://openalex.org/W4386076661","https://openalex.org/W4388208942","https://openalex.org/W4390873732","https://openalex.org/W4402727803","https://openalex.org/W4402733588","https://openalex.org/W7133182950","https://openalex.org/W7133188694"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-07T06:14:10.401900","created_date":"2026-07-01T00:00:00"}