{"id":"https://openalex.org/W4396779975","doi":"https://doi.org/10.1007/s00138-024-01547-x","title":"Multi sentence description of complex manipulation action videos","display_name":"Multi sentence description of complex manipulation action videos","publication_year":2024,"publication_date":"2024-05-09","ids":{"openalex":"https://openalex.org/W4396779975","doi":"https://doi.org/10.1007/s00138-024-01547-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00138-024-01547-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-024-01547-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01547-x.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01547-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089770964","display_name":"Fatemeh Ziaeetabar","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]},{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["DE","IR"],"is_corresponding":true,"raw_author_name":"Fatemeh Ziaeetabar","raw_affiliation_strings":["Faculty of Computer Engineering, Amirkabir University of Technology, Tehran, Iran","III. Physics Institute, University of G\u00f6ttingen, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"III. Physics Institute, University of G\u00f6ttingen, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043747222","display_name":"Reza Safabakhsh","orcid":"https://orcid.org/0000-0002-4937-8026"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Reza Safabakhsh","raw_affiliation_strings":["Faculty of Computer Engineering, Amirkabir University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015201403","display_name":"Saeedeh Momtazi","orcid":"https://orcid.org/0000-0002-8110-1342"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Saeedeh Momtazi","raw_affiliation_strings":["Faculty of Computer Engineering, Amirkabir University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026724617","display_name":"Minija Tamo\u0161i\u016bnait\u0117","orcid":"https://orcid.org/0000-0003-2996-3612"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]},{"id":"https://openalex.org/I188730046","display_name":"Vytautas Magnus University","ror":"https://ror.org/04y7eh037","country_code":"LT","type":"education","lineage":["https://openalex.org/I188730046"]}],"countries":["DE","LT"],"is_corresponding":false,"raw_author_name":"Minija Tamosiunaite","raw_affiliation_strings":["Faculty of Informatics, Vytautas Magnus University, Kaunas, Lithuania","III. Physics Institute, University of G\u00f6ttingen, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Vytautas Magnus University, Kaunas, Lithuania","institution_ids":["https://openalex.org/I188730046"]},{"raw_affiliation_string":"III. Physics Institute, University of G\u00f6ttingen, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023811677","display_name":"Florentin W\u00f6rg\u00f6tter","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florentin W\u00f6rg\u00f6tter","raw_affiliation_strings":["III. Physics Institute, University of G\u00f6ttingen, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"III. Physics Institute, University of G\u00f6ttingen, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089770964"],"corresponding_institution_ids":["https://openalex.org/I158248296","https://openalex.org/I74656192"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":0.5073,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62083669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"35","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9907000064849854,"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/computer-science","display_name":"Computer science","score":0.8523862361907959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703607797622681},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5359886884689331},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47782209515571594},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4698416590690613},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45132604241371155},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44993144273757935},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4391908049583435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3779190480709076},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3731396198272705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523862361907959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703607797622681},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5359886884689331},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47782209515571594},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4698416590690613},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45132604241371155},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44993144273757935},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4391908049583435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3779190480709076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3731396198272705},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s00138-024-01547-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-024-01547-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01547-x.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/143604","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/143604","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"yes"},{"id":"pmh:oai:vdu.lt:20.500.12259/266634","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.12259/266634","pdf_url":null,"source":{"id":"https://openalex.org/S7407055361","display_name":"Vytautas Magnus University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"}],"best_oa_location":{"id":"doi:10.1007/s00138-024-01547-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-024-01547-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01547-x.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321870","display_name":"Georg-August-Universit\u00e4t G\u00f6ttingen","ror":"https://ror.org/01y9bpm73"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396779975.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1596841185","https://openalex.org/W1601567445","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1964108206","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2124807415","https://openalex.org/W2125707784","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2157435188","https://openalex.org/W2342277278","https://openalex.org/W2425121537","https://openalex.org/W2549599535","https://openalex.org/W2559085405","https://openalex.org/W2731627339","https://openalex.org/W2736791688","https://openalex.org/W2896736483","https://openalex.org/W2952132648","https://openalex.org/W2962681491","https://openalex.org/W2963576560","https://openalex.org/W2963811641","https://openalex.org/W2963843052","https://openalex.org/W2963860638","https://openalex.org/W2963916161","https://openalex.org/W2964241990","https://openalex.org/W2979437663","https://openalex.org/W2981773282","https://openalex.org/W3021013305","https://openalex.org/W3034679267","https://openalex.org/W3092659741","https://openalex.org/W3217340782","https://openalex.org/W4285606530","https://openalex.org/W4288083805","https://openalex.org/W4312463400","https://openalex.org/W4386057717","https://openalex.org/W4386066385","https://openalex.org/W4386076176","https://openalex.org/W6610910477"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"Abstract":[0],"Automatic":[1],"video":[2,38,54,106,155],"description":[3,39,170],"necessitates":[4],"generating":[5],"natural":[6],"language":[7,124],"statements":[8],"that":[9,35,189],"encapsulate":[10],"the":[11,29,70,109,119,123,139,143,150],"actions,":[12,58,74],"events,":[13],"and":[14,91,122,146,152],"objects":[15],"within":[16,105],"a":[17,33,87,115],"video.":[18],"An":[19],"essential":[20],"human":[21],"capability":[22],"in":[23],"describing":[24],"videos":[25,173],"is":[26],"to":[27,66,77,137,168,174],"vary":[28],"level":[30],"of":[31,56,62,73,141,154],"detail,":[32],"feature":[34],"existing":[36],"automatic":[37],"methods,":[40],"which":[41],"typically":[42],"generate":[43],"single,":[44],"fixed-level":[45],"detail":[46,63],"sentences,":[47],"often":[48],"overlook.":[49],"This":[50],"work":[51],"delves":[52],"into":[53],"descriptions":[55,156,195],"manipulation":[57],"where":[59],"varying":[60],"levels":[61],"are":[64],"crucial":[65],"conveying":[67],"information":[68],"about":[69],"hierarchical":[71],"structure":[72],"also":[75],"pertinent":[76],"contemporary":[78],"robot":[79],"learning":[80],"techniques.":[81],"We":[82],"initially":[83],"propose":[84],"two":[85],"frameworks:":[86],"hybrid":[88,96,144],"statistical":[89,128,145],"model":[90],"an":[92,133],"end-to-end":[93,110,147],"approach.":[94],"The":[95],"method,":[97,111],"requiring":[98],"significantly":[99],"less":[100],"data,":[101],"statistically":[102],"models":[103],"uncertainties":[104],"clips.":[107],"Conversely,":[108],"more":[112,193],"data-intensive,":[113],"establishes":[114],"direct":[116],"link":[117],"between":[118],"visual":[120],"encoder":[121],"decoder,":[125],"bypassing":[126],"any":[127],"processing.":[129],"Furthermore,":[130],"we":[131],"introduce":[132],"Integrated":[134],"Method,":[135],"aiming":[136],"amalgamate":[138],"benefits":[140],"both":[142],"approaches,":[148],"enhancing":[149],"adaptability":[151],"depth":[153],"across":[157],"different":[158],"data":[159],"availability":[160],"scenarios.":[161],"All":[162],"three":[163],"frameworks":[164],"utilize":[165],"LSTM":[166],"stacks":[167],"facilitate":[169],"granularity,":[171],"allowing":[172],"be":[175],"depicted":[176],"through":[177],"either":[178],"succinct":[179],"single":[180],"sentences":[181],"or":[182],"elaborate":[183],"multi-sentence":[184],"narratives.":[185],"Quantitative":[186],"results":[187],"demonstrate":[188],"these":[190],"methods":[191],"produce":[192],"realistic":[194],"than":[196],"other":[197],"competing":[198],"approaches.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}