{"id":"https://openalex.org/W4391877721","doi":"https://doi.org/10.1109/comsnets59351.2024.10427136","title":"Video Captioning using Spatio-temporal Graphs: An Encoder-Decoder Approach","display_name":"Video Captioning using Spatio-temporal Graphs: An Encoder-Decoder Approach","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4391877721","doi":"https://doi.org/10.1109/comsnets59351.2024.10427136"},"language":"en","primary_location":{"id":"doi:10.1109/comsnets59351.2024.10427136","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/comsnets59351.2024.10427136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","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/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":true,"raw_author_name":"Vibhor Sharma","raw_affiliation_strings":["National Institute of Technology,CSE,Delhi,India","CSE, National Institute of Technology, Delhi, India"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology,CSE,Delhi,India","institution_ids":["https://openalex.org/I44635919"]},{"raw_affiliation_string":"CSE, National Institute of Technology, Delhi, India","institution_ids":["https://openalex.org/I44635919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004894915","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":false,"raw_author_name":"Anurag Singh","raw_affiliation_strings":["National Institute of Technology,CSE,Delhi,India","CSE, National Institute of Technology, Delhi, India"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology,CSE,Delhi,India","institution_ids":["https://openalex.org/I44635919"]},{"raw_affiliation_string":"CSE, National Institute of Technology, Delhi, 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":["University of Milan,CSE,Milan,Italy","CSE, University of Milan, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"University of Milan,CSE,Milan,Italy","institution_ids":["https://openalex.org/I189158943"]},{"raw_affiliation_string":"CSE, University of Milan, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009436918"],"corresponding_institution_ids":["https://openalex.org/I44635919"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0145238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"424","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9972000122070312,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9905999898910522,"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":0.8909966945648193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8273080587387085},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7804661393165588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3701033592224121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2771652936935425},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08956125378608704},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06075906753540039}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8909966945648193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273080587387085},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7804661393165588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3701033592224121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2771652936935425},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08956125378608704},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06075906753540039}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/comsnets59351.2024.10427136","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/comsnets59351.2024.10427136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2133512280","https://openalex.org/W2330246314","https://openalex.org/W2559542432","https://openalex.org/W2766375149","https://openalex.org/W2808203533","https://openalex.org/W2949817882","https://openalex.org/W2962681491","https://openalex.org/W2964241990","https://openalex.org/W3019301826","https://openalex.org/W3184377166","https://openalex.org/W4206490662","https://openalex.org/W4281833049"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314"],"abstract_inverted_index":{"To":[0],"understand":[1],"the":[2,5,10,19,49,62,82,111],"content":[3],"in":[4,9,36,48,58,113],"video,":[6],"describing":[7],"it":[8,80],"form":[11],"of":[12,18,25,51,103],"natural":[13,115],"language":[14],"is":[15,41,81,90,120],"also":[16],"one":[17],"essential":[20],"requirements.":[21],"A":[22],"video":[23,112],"consists":[24],"frames":[26,52],"showing":[27],"different":[28],"objects":[29,33],"and":[30,39,76,100,127],"actions.":[31],"These":[32],"can":[34,67],"change":[35],"each":[37],"frame,":[38],"there":[40],"a":[42,54,59,93,114],"time-dependent":[43],"sequence":[44,50],"between":[45,64,85],"objects.":[46,86,105],"Objects":[47],"have":[53],"temporal":[55,77],"relationship.":[56],"Actions":[57],"frame":[60],"are":[61],"interactions":[63],"objects,":[65],"which":[66,96],"be":[68],"easily":[69],"understood":[70],"using":[71,92,122],"spatial":[72,75],"relationships.":[73],"When":[74],"aspects":[78],"combine,":[79],"Spatio-temporal":[83,94,108],"relationships":[84],"Analyzing":[87],"this":[88],"relationship":[89],"done":[91],"graph,":[95],"integrates":[97],"both":[98],"visual":[99],"motion":[101],"features":[102],"detected":[104],"An":[106],"integrated":[107],"graph":[109],"describes":[110],"sentence.":[116],"The":[117],"generated":[118],"sentence":[119],"evaluated":[121],"Metrics":[123],"like":[124],"BLEU@4,":[125],"METEOR,":[126],"CIDEr.":[128]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}