{"id":"https://openalex.org/W4415708234","doi":"https://doi.org/10.1109/icme59968.2025.11209997","title":"Tell and Show: A Multimodal Guidance Method for Instructional Video Planning","display_name":"Tell and Show: A Multimodal Guidance Method for Instructional Video Planning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708234","doi":"https://doi.org/10.1109/icme59968.2025.11209997"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5071665533","display_name":"Mingzhe Zhang","orcid":"https://orcid.org/0009-0004-2758-4146"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhe Zhang","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629240","display_name":"Yinghui Zhang","orcid":"https://orcid.org/0000-0002-5764-3272"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Zhang","raw_affiliation_strings":["Beijing Normal University,College of Education for the Future,Zhuhai,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,College of Education for the Future,Zhuhai,China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109947746","display_name":"Feng\u2010Xiang Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengxiang Ge","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071665533"],"corresponding_institution_ids":["https://openalex.org/I25254941"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31028529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9004999995231628,"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":0.9004999995231628,"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":0.04450000077486038,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.01360000018030405,"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/task","display_name":"Task (project management)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4821999967098236},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4327000081539154},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4106000065803528},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.39250001311302185},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3882000148296356},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234999775886536},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47040000557899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44279998540878296},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4106000065803528},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.39250001311302185},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3882000148296356},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2031688197","https://openalex.org/W2099614498","https://openalex.org/W2963465031","https://openalex.org/W2964094654","https://openalex.org/W3106768499","https://openalex.org/W3180355996","https://openalex.org/W3203256294","https://openalex.org/W4312478760","https://openalex.org/W4386057769","https://openalex.org/W4386065873","https://openalex.org/W4386075710","https://openalex.org/W4386076369","https://openalex.org/W4387806972","https://openalex.org/W4390873991","https://openalex.org/W4390874412"],"related_works":[],"abstract_inverted_index":{"The":[0],"abundance":[1],"of":[2,130],"instructional":[3],"videos":[4,20],"and":[5,25,35,44,67,105,123,126],"their":[6],"accompanying":[7],"narratives":[8],"presents":[9,27],"a":[10,37,82],"valuable":[11],"resource":[12],"for":[13,21,137],"understanding":[14],"procedural":[15,23,47,115],"activities.":[16],"However,":[17],"leveraging":[18],"these":[19],"accurate":[22],"comprehending":[24],"following":[26],"challenges.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,80],"introduce":[33,94],"Tell":[34],"Show,":[36],"novel":[38],"multimodal":[39],"guidance":[40,85],"framework":[41],"that":[42],"predicts":[43],"previews":[45,136],"future":[46],"steps":[48],"by":[49],"integrating":[50],"visual":[51,135],"observations":[52],"with":[53,134],"textual":[54],"task":[55,139],"goals.":[56],"Our":[57,111],"approach":[58],"addresses":[59],"challenges":[60],"such":[61],"as":[62],"weak":[63],"step":[64,70,121],"boundary":[65],"detection":[66],"variations":[68],"in":[69,108,120],"ordering":[71],"through":[72],"step-aware":[73],"prompt":[74],"learning,":[75],"enhancing":[76],"semantic":[77,106],"alignment.":[78],"Additionally,":[79],"propose":[81],"multi-level":[83],"goal-oriented":[84],"module":[86],"to":[87],"improve":[88],"long-term":[89],"action":[90,124],"recognition.":[91],"We":[92],"also":[93],"the":[95,128],"Temporal-Spatial-Semantic":[96],"Fusion":[97],"Transformer":[98],"Block":[99],"(TSSB),":[100],"which":[101],"ensures":[102],"temporal-spatial":[103],"consistency":[104],"alignment":[107],"video":[109],"synthesis.":[110],"method":[112],"significantly":[113],"advances":[114],"reasoning,":[116],"achieving":[117],"promising":[118],"results":[119],"forecasting":[122],"recognition,":[125],"demonstrating":[127],"effectiveness":[129],"combining":[131],"text-based":[132],"planning":[133],"complex":[138],"completion.":[140]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}