{"id":"https://openalex.org/W4415538804","doi":"https://doi.org/10.1145/3746027.3754999","title":"InstructStep: Fine-Grained Localization of Step Content and Relation in Instructional Video","display_name":"InstructStep: Fine-Grained Localization of Step Content and Relation in Instructional Video","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538804","doi":"https://doi.org/10.1145/3746027.3754999"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":"https://openalex.org/A5120131964","display_name":"Wangsheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangsheng He","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0009-9845-7888","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071889746","display_name":"Wanru Xu","orcid":"https://orcid.org/0000-0003-2206-5051"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanru Xu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2206-5051","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131965","display_name":"Ping Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Guo","raw_affiliation_strings":["Intel Labs China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1166-4042","affiliations":[{"raw_affiliation_string":"Intel Labs China, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100298934","display_name":"Zhenjiang Miao","orcid":"https://orcid.org/0000-0001-8032-5769"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjiang Miao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8032-5769","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752649","display_name":"Yi Tian","orcid":"https://orcid.org/0000-0001-6054-7970"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Tian","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, Beijing Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0001-6054-7970","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, Beijing Jiaotong University, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32846054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3163","last_page":"3172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"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":0.9983999729156494,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9794999957084656,"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/relation","display_name":"Relation (database)","score":0.8033000230789185},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.6122000217437744},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5406000018119812},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47839999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183000087738037},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.8033000230789185},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.30979999899864197},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G351457812","display_name":null,"funder_award_id":"62376021,62006015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6685202050","display_name":null,"funder_award_id":"F2025105036","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322163","display_name":"Natural Science Foundation of Hebei Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2765658575","https://openalex.org/W2798354744","https://openalex.org/W2904824998","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2964023933","https://openalex.org/W2997429269","https://openalex.org/W3011215845","https://openalex.org/W3025323587","https://openalex.org/W3034368386","https://openalex.org/W3034743747","https://openalex.org/W3088744711","https://openalex.org/W3200217958","https://openalex.org/W3207732590","https://openalex.org/W4285290969","https://openalex.org/W4298364821","https://openalex.org/W4308731558","https://openalex.org/W4327852044","https://openalex.org/W4360600216","https://openalex.org/W4385804904","https://openalex.org/W4392193048","https://openalex.org/W4392337501","https://openalex.org/W4392826163","https://openalex.org/W4399426547","https://openalex.org/W4402754238","https://openalex.org/W4412888584"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"methods":[1],"for":[2,25,40,60],"video":[3,9,35],"answer":[4],"localization":[5],"(VAL)":[6],"in":[7,118,127,182,189],"instructional":[8],"focus":[10],"predominantly":[11],"on":[12,199],"coarse-grained":[13],"themes,":[14],"failing":[15],"to":[16,73,131,162,180,187],"address":[17,47],"detailed":[18],"step":[19,41,86,125,133,160,183,190],"content":[20,36,75,87,184],"and":[21,43,65,76,88,122,153,159,165,185],"inter-step":[22,44],"relation":[23,89],"crucial":[24],"effective":[26],"comprehension.":[27],"Current":[28],"datasets,":[29],"such":[30],"as":[31],"MedVidQA,":[32],"primarily":[33],"capture":[34,163],"but":[37],"lack":[38],"annotations":[39],"structure":[42],"relation.":[45,77,191],"To":[46,92],"this":[48,97],"gap,":[49],"we":[50,79,99],"introduce":[51],"InstructStep,":[52],"a":[53,81,101,124],"newly":[54],"proposed":[55],"VAL":[56,71],"task,":[57,98],"specifically":[58],"designed":[59],"Instructional":[61],"Video":[62],"Step":[63],"Content":[64],"Relation":[66],"Localization.":[67],"It":[68],"extends":[69],"original":[70],"task":[72],"step-centric":[74,166],"Accordingly,":[78],"create":[80],"InstructStep":[82],"Dataset":[83],"with":[84,175],"fine-grained":[85,164],"QA":[90],"pairs.":[91],"tackle":[93],"the":[94,119,128,171],"challenges":[95],"of":[96,173,178],"propose":[100],"Step-Centric":[102],"Multi-Level":[103],"Knowledge":[104],"Distillation":[105],"(SC-MLKD)":[106],"approach":[107],"that:":[108],"(1)":[109],"A":[110],"two-stage":[111],"training":[112],"strategy":[113],"that":[114],"generates":[115],"step-specific":[116],"summaries":[117],"first":[120],"stage":[121,130],"introduces":[123],"branch":[126],"second":[129],"learn":[132],"relations.":[134],"This":[135],"is":[136],"applied":[137],"only":[138],"during":[139],"training,":[140],"ensuring":[141],"no":[142],"additional":[143],"inference":[144],"time.":[145],"(2)":[146],"Multi-level":[147],"knowledge":[148],"distillation,":[149,155],"including":[150],"feature,":[151],"relation,":[152],"response":[154],"across":[156],"visual,":[157],"text":[158],"branches":[161],"features.":[167],"Comprehensive":[168],"experiments":[169],"demonstrate":[170],"efficiency":[172],"SC-MLKD,":[174],"notable":[176],"gains":[177],"up":[179,186],"5.83%":[181],"5.9%":[188],"The":[192],"dataset":[193],"have":[194],"been":[195],"made":[196],"publicly":[197],"available":[198],"https://github.com/hewangsh/InstructStep":[200]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}