{"id":"https://openalex.org/W7165107170","doi":"https://doi.org/10.1016/j.cviu.2026.104853","title":"Semantic-Weighted Spatio-Temporal Graphs for Structured Video Understanding and Captioning","display_name":"Semantic-Weighted Spatio-Temporal Graphs for Structured Video Understanding and Captioning","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165107170","doi":"https://doi.org/10.1016/j.cviu.2026.104853"},"language":"en","primary_location":{"id":"doi:10.1016/j.cviu.2026.104853","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104853","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"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":"Computer Vision and Image Understanding","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/A5009436918","display_name":"Vibhor Sharma","orcid":"https://orcid.org/0000-0002-7365-1846"},"institutions":[{"id":"https://openalex.org/I44635919","display_name":"National Institute of Technology Delhi","ror":"https://ror.org/032twef21","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152752","https://openalex.org/I44635919"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vibhor Sharma","raw_affiliation_strings":["Department of Computer Science and Engineering, National Institute of Technology Delhi, New Delhi, 110036, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Institute of Technology Delhi, New Delhi, 110036, India","institution_ids":["https://openalex.org/I44635919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135089468","display_name":"Anurag Singh","orcid":"https://orcid.org/0000-0002-3639-2777"},"institutions":[{"id":"https://openalex.org/I44635919","display_name":"National Institute of Technology Delhi","ror":"https://ror.org/032twef21","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152752","https://openalex.org/I44635919"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anurag Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, National Institute of Technology Delhi, New Delhi, 110036, India"],"raw_orcid":"https://orcid.org/0000-0003-3582-0319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Institute of Technology Delhi, New Delhi, 110036, India","institution_ids":["https://openalex.org/I44635919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002723662","display_name":"Sabrina Gaito","orcid":"https://orcid.org/0000-0003-3779-2809"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabrina Gaito","raw_affiliation_strings":["Department of Computer Science, University of Milan, Milan, 20122, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Milan, Milan, 20122, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5135089468"],"corresponding_institution_ids":["https://openalex.org/I44635919"],"apc_list":{"value":2090,"currency":"USD","value_usd":2090},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61163681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"270","issue":null,"first_page":"104853","last_page":"104853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9868000149726868,"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":0.9868000149726868,"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":0.0026000000070780516,"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":0.0017000000225380063,"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/closed-captioning","display_name":"Closed captioning","score":0.635200023651123},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6057000160217285},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5540000200271606},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5468000173568726},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49470001459121704},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3898000121116638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410000205039978},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.635200023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607699990272522},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5540000200271606},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4968999922275543},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4674000144004822},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.cviu.2026.104853","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104853","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"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":"Computer Vision and Image Understanding","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":24,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W2808203533","https://openalex.org/W2953461088","https://openalex.org/W2962958773","https://openalex.org/W2963576560","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3164646408","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4281560470","https://openalex.org/W4286488082","https://openalex.org/W4385825476","https://openalex.org/W4386122702","https://openalex.org/W4387745577","https://openalex.org/W4390100115","https://openalex.org/W4400269657","https://openalex.org/W4400748621","https://openalex.org/W4400850904","https://openalex.org/W4402754015","https://openalex.org/W4403791986","https://openalex.org/W4403900829","https://openalex.org/W4406983084"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-06-19T00:00:00"}
