{"id":"https://openalex.org/W7138089223","doi":"https://doi.org/10.1609/aaai.v40i11.37821","title":"Transformer with Controlled Attention for Synchronous Motion Captioning","display_name":"Transformer with Controlled Attention for Synchronous Motion Captioning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138089223","doi":"https://doi.org/10.1609/aaai.v40i11.37821"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37821","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37821","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37821","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Karim Radouane","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karim Radouane","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sylvie Ranwez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sylvie Ranwez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Julien Lagarde","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Lagarde","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Andon Tchechmedjiev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andon Tchechmedjiev","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44046628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"8686","last_page":"8693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5375999808311462,"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":0.5375999808311462,"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/T12290","display_name":"Human Motion and Animation","score":0.3246999979019165,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.047600001096725464,"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/interpretability","display_name":"Interpretability","score":0.6859999895095825},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.67330002784729},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4977000057697296},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3774999976158142},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.3368000090122223},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3239000141620636},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.3109999895095825},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.30790001153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979000210762024},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6859999895095825},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.67330002784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553600013256073},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4977000057697296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C28944840","wikidata":"https://www.wikidata.org/wiki/Q1256545","display_name":"Synchro","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37821","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37821","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37821","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37821","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5938864946365356,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,63,155],"paper,":[2],"we":[3,157],"address":[4],"a":[5,15,88,106,159],"challenging":[6],"task,":[7,156],"synchronous":[8,170],"motion":[9,21,89,128],"captioning,":[10],"that":[11,70],"aim":[12,93],"to":[13,26,46,74,84,94,104],"generate":[14],"language":[16,33],"description":[17],"synchronized":[18],"with":[19,126],"human":[20,127],"sequences.":[22,129],"This":[23],"task":[24],"pertains":[25],"numerous":[27],"applications,":[28],"such":[29],"as":[30],"aligned":[31,58],"sign":[32],"transcription":[34],"and":[35,39,49,57,67,103,147],"unsupervised":[36],"action":[37],"segmentation":[38],"temporal":[40],"grounding.":[41],"Our":[42],"method":[43],"introduces":[44],"mechanisms":[45],"control":[47],"self-":[48],"cross-attention":[50],"distributions":[51],"of":[52,87,98,116,135,162,166,169],"the":[53,72,79,85,113,132,141,167,174],"Transformer,":[54],"allowing":[55],"interpretability":[56],"text":[59,122,171],"generation.":[60],"We":[61,130],"achieve":[62],"through":[64,138],"masking":[65],"strategies":[66],"structuring":[68],"losses":[69],"push":[71],"model":[73],"maximize":[75],"attention":[76,101,108],"only":[77],"on":[78,140],"most":[80],"important":[81],"frames":[82],"contributing":[83],"generation":[86,123,172],"word.":[90],"These":[91],"constraints":[92],"prevent":[95],"undesired":[96],"mixing":[97],"information":[99],"in":[100,124,173],"maps":[102],"provide":[105,158],"monotonic":[107],"distribution":[109],"across":[110],"tokens.":[111],"Thus,":[112],"cross":[114],"attentions":[115],"tokens":[117],"are":[118],"used":[119],"for":[120,154],"progressive":[121],"synchronization":[125],"demonstrate":[131],"superior":[133],"performance":[134],"our":[136],"approach":[137],"evaluation":[139,151],"two":[142],"available":[143],"benchmark":[144],"datasets,":[145],"KIT-ML":[146],"HumanML3D.":[148],"As":[149],"visual":[150,164],"is":[152],"essential":[153],"comprehensive":[160],"set":[161],"animated":[163],"illustrations":[165],"output":[168],"code":[175],"repository.":[176]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
