{"id":"https://openalex.org/W4411631888","doi":"https://doi.org/10.1145/3731715.3733438","title":"Step-wise Soft Alignment Enhanced Procedural Text Generation from Long Instructional Videos","display_name":"Step-wise Soft Alignment Enhanced Procedural Text Generation from Long Instructional Videos","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631888","doi":"https://doi.org/10.1145/3731715.3733438"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Zhihao Wang","orcid":"https://orcid.org/0009-0001-7622-0320"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Wang","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-7622-0320","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7553-6916","affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-5242-0467","affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065941595","display_name":"Xiaohui Tao","orcid":"https://orcid.org/0000-0002-0020-077X"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaohui Tao","raw_affiliation_strings":["University of Southern Queensland, Springfield, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0020-077X","affiliations":[{"raw_affiliation_string":"University of Southern Queensland, Springfield, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079797505","display_name":"Jianquan Liu","orcid":"https://orcid.org/0000-0003-4303-9020"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianquan Liu","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4303-9020","affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1377","last_page":"1385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9983999729156494,"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":0.968500018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719333171844482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4593110680580139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4125373363494873},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35296785831451416},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32248327136039734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719333171844482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593110680580139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4125373363494873},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35296785831451416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32248327136039734}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G536584589","display_name":null,"funder_award_id":"62276196 and 62271361","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2108325777","https://openalex.org/W2194775991","https://openalex.org/W2963916161","https://openalex.org/W2964110616","https://openalex.org/W3035237998","https://openalex.org/W3035480894","https://openalex.org/W3167308647","https://openalex.org/W3186223381","https://openalex.org/W3189265444","https://openalex.org/W3204119129","https://openalex.org/W3207001124","https://openalex.org/W3208601917","https://openalex.org/W3217340782","https://openalex.org/W4214663214","https://openalex.org/W4372260221","https://openalex.org/W4382240304","https://openalex.org/W4382464395","https://openalex.org/W4385617545","https://openalex.org/W4385774762","https://openalex.org/W4389519587","https://openalex.org/W4391651317","https://openalex.org/W4392623252","https://openalex.org/W4393152873","https://openalex.org/W4393158799","https://openalex.org/W4399423097","https://openalex.org/W4400850904","https://openalex.org/W4402780269","https://openalex.org/W6601846001"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"With":[0],"the":[1,100,120,151,160,169],"rise":[2],"of":[3,40,153,171,176],"generative":[4],"models,":[5],"video-language":[6],"cross-modal":[7],"applications":[8],"have":[9],"seen":[10],"significant":[11],"growth.":[12],"Generating":[13],"procedural":[14,115,124,154],"text":[15,125,155],"from":[16],"instructional":[17],"videos":[18],"has":[19],"become":[20],"a":[21,25,66,72,105,138],"crucial":[22],"task,":[23],"playing":[24],"key":[26],"role":[27],"in":[28,65,184],"both":[29],"understanding":[30],"visual":[31,111],"scenes":[32],"and":[33,113,126,164,180],"supporting":[34],"practical":[35],"applications.":[36],"The":[37,132],"sequential":[38],"nature":[39],"video":[41,127],"clips":[42,64,128],"is":[43,74],"particularly":[44],"important,":[45],"as":[46,68,137,143],"entities":[47],"may":[48],"appear":[49],"across":[50],"multiple":[51],"clips,":[52],"reflecting":[53],"fine-grained":[54],"intra-modal":[55],"self-similarity.":[56],"However,":[57],"most":[58],"existing":[59],"training":[60],"methods":[61],"treat":[62],"other":[63],"sequence":[67],"negative":[69],"samples":[70],"when":[71],"target":[73],"specified,":[75],"neglecting":[76],"their":[77],"step-wise":[78,106,121],"correlations.":[79],"To":[80],"address":[81],"this":[82],"limitation,":[83],"we":[84],"introduce":[85],"Step-wise":[86],"Soft":[87],"Alignment":[88],"via":[89],"OpTimal":[90],"TrAnsport":[91],"(SATA),":[92],"which":[93],"constructs":[94],"soft":[95,144],"positive":[96],"pairs":[97,142],"to":[98,178,182],"mitigate":[99],"issue.":[101],"SATA":[102],"first":[103],"generates":[104],"similarity":[107],"matrix":[108],"by":[109],"leveraging":[110],"representations":[112],"generated":[114],"text.":[116],"It":[117],"then":[118],"aligns":[119],"distributions":[122],"between":[123],"using":[129],"optimal":[130],"transport.":[131],"resulting":[133],"transport":[134],"distance":[135],"serves":[136],"weight,":[139],"treating":[140],"these":[141],"positives":[145],"for":[146],"contrastive":[147],"learning,":[148],"ultimately":[149],"improving":[150],"accuracy":[152],"generation.":[156],"Our":[157],"experiments":[158],"on":[159],"publicly":[161],"available":[162],"YouCookII":[163],"ActivityNet":[165],"Captions":[166],"datasets":[167],"demonstrate":[168],"effectiveness":[170],"SATA,":[172],"achieving":[173],"absolute":[174],"improvements":[175],"0.5%":[177],"1.7%":[179],"0.6%":[181],"14.9%":[183],"paragraph-level":[185],"evaluation,":[186],"respectively.":[187]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}