{"id":"https://openalex.org/W4410536058","doi":"https://doi.org/10.1109/tcsvt.2025.3571422","title":"Scenario-Aware Multimodal Chain-of-Thought Prompting for Rationales of VideoSocial Relations","display_name":"Scenario-Aware Multimodal Chain-of-Thought Prompting for Rationales of VideoSocial Relations","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410536058","doi":"https://doi.org/10.1109/tcsvt.2025.3571422"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3571422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3571422","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5078167012","display_name":"Penggang Qin","orcid":"https://orcid.org/0000-0003-1538-0475"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Penggang Qin","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1538-0475","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I143868143","https://openalex.org/I126520041"]},{"raw_affiliation_string":"Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Tong Xu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4246-5386","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I143868143","https://openalex.org/I126520041"]},{"raw_affiliation_string":"Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Zhang","orcid":"https://orcid.org/0009-0007-2579-8783"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Chao Zhang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-2579-8783","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I143868143","https://openalex.org/I126520041"]},{"raw_affiliation_string":"Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040616611","display_name":"Heda Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heda Wang","raw_affiliation_strings":["Xiaohongshu, Shanghai, China","Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107062676","display_name":"Yao Hu","orcid":"https://orcid.org/0009-0006-1274-7111"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":["Xiaohongshu, Shanghai, China","Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Enhong Chen","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4835-4102","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I143868143","https://openalex.org/I126520041"]},{"raw_affiliation_string":"Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7004308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":"11","first_page":"11598","last_page":"11612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9797000288963318,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9797000288963318,"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/computer-science","display_name":"Computer science","score":0.6665442585945129},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41909319162368774},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3793741464614868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3760516941547394},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3681512475013733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3502093553543091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665442585945129},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41909319162368774},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3793741464614868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3760516941547394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3681512475013733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3502093553543091}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3571422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3571422","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3604000827","display_name":null,"funder_award_id":"62222213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4442529403","display_name":null,"funder_award_id":"U22B2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":40,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2011605810","https://openalex.org/W2075585362","https://openalex.org/W2194775991","https://openalex.org/W2332488709","https://openalex.org/W2421935140","https://openalex.org/W2507009361","https://openalex.org/W2884913105","https://openalex.org/W2885138528","https://openalex.org/W2951019013","https://openalex.org/W2958301808","https://openalex.org/W2963542293","https://openalex.org/W2964015378","https://openalex.org/W2965373594","https://openalex.org/W3021553284","https://openalex.org/W3035124602","https://openalex.org/W3035524453","https://openalex.org/W3155721152","https://openalex.org/W3197270443","https://openalex.org/W3198377975","https://openalex.org/W3205786327","https://openalex.org/W3207061104","https://openalex.org/W4229494842","https://openalex.org/W4285110863","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312558481","https://openalex.org/W4386057718","https://openalex.org/W4387968143","https://openalex.org/W4389169598","https://openalex.org/W4390590848","https://openalex.org/W4392223601","https://openalex.org/W4393146968","https://openalex.org/W4393149666","https://openalex.org/W4394951233","https://openalex.org/W4401634027","https://openalex.org/W4402557613","https://openalex.org/W4402754270","https://openalex.org/W4405934112","https://openalex.org/W4408399448"],"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":{"Recently,":[0],"audiences":[1],"have":[2],"increasingly":[3],"watched":[4],"diverse":[5],"dramas":[6],"and":[7,25,37,74,109,146,162,173],"movies":[8],"on":[9,80],"streaming":[10],"platforms,":[11],"prompting":[12],"platform":[13],"administrators":[14],"to":[15,176],"enhance":[16],"their":[17],"understanding":[18],"of":[19,58],"video":[20,63,127],"semantics.":[21],"In":[22,115],"particular,":[23],"capturing":[24],"interpreting":[26],"social":[27,48,105,112,124,135,143],"relations":[28,49,125],"among":[29],"characters":[30],"is":[31],"critical":[32],"for":[33,122],"content-driven":[34],"intelligent":[35],"services":[36],"enhancing":[38],"user":[39],"experience.":[40],"However,":[41],"most":[42],"existing":[43],"research":[44,73],"has":[45],"solely":[46],"approached":[47],"recognition":[50,137],"as":[51],"a":[52],"classification":[53,171],"problem,":[54],"without":[55],"justifiable":[56],"interpretation":[57],"prediction":[59],"results":[60],"within":[61],"the":[62,75],"context.":[64],"To":[65],"address":[66],"this":[67,116],"issue,":[68],"we":[69,83,118,130,151],"study":[70],"cognitive":[71,101],"science":[72],"Chain-of-Thought":[76],"(CoT)":[77],"strategy.":[78],"Based":[79],"these":[81],"foundations,":[82],"propose":[84],"SaMo-CoT,":[85],"an":[86,132],"approach":[87,98],"that":[88,139],"leverages":[89],"large":[90],"language":[91],"models":[92],"(LLMs)":[93],"in":[94,107,126,170],"step-by-step":[95],"reasoning.":[96],"This":[97],"simulates":[99],"human":[100],"processes":[102],"by":[103,158],"combining":[104],"scenarios":[106],"videos":[108],"incorporating":[110],"empirical":[111],"interaction":[113],"knowledge.":[114],"way,":[117],"enable":[119],"verbal":[120,153],"rationales":[121],"determining":[123],"understanding.":[128],"Furthermore,":[129],"present":[131],"innovative":[133],"doubly-right":[134],"relation":[136,144],"framework":[138],"predicts":[140],"both":[141],"correct":[142,147],"labels":[145],"scenario":[148],"rationales.":[149],"Specifically,":[150],"translate":[152],"CoT":[154,157],"into":[155],"multimodal":[156],"leveraging":[159],"scenario-aware":[160],"prompts":[161],"contrastive":[163],"learning.":[164],"Extensive":[165],"experiments":[166],"demonstrate":[167],"significant":[168],"improvements":[169],"accuracy":[172],"interpretability":[174],"compared":[175],"traditional":[177],"approaches.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
