{"id":"https://openalex.org/W4403792253","doi":"https://doi.org/10.1145/3664647.3681712","title":"Peeling Back the Layers: Interpreting the Storytelling of ViT","display_name":"Peeling Back the Layers: Interpreting the Storytelling of ViT","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792253","doi":"https://doi.org/10.1145/3664647.3681712"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5102532881","display_name":"Jingjie Zeng","orcid":"https://orcid.org/0009-0002-5412-2348"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjie Zeng","raw_affiliation_strings":["Dalian University of Technology, Dalian, LiaoNing, China"],"raw_orcid":"https://orcid.org/0009-0002-5412-2348","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, LiaoNing, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051597671","display_name":"Zhihao Yang","orcid":"https://orcid.org/0000-0001-6186-2024"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Yang","raw_affiliation_strings":["Dalian University of Technology, Dalian, LiaoNing, China"],"raw_orcid":"https://orcid.org/0000-0001-6186-2024","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, LiaoNing, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101246010","display_name":"Qi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yang","raw_affiliation_strings":["Dalian University of Technology, Dalian, LiaoNing, China"],"raw_orcid":"https://orcid.org/0009-0002-8597-122X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, LiaoNing, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032091007","display_name":"Liang Yang","orcid":"https://orcid.org/0000-0002-5557-7515"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yang","raw_affiliation_strings":["Dalian University of Technology &amp; Ministry of Education, Key Laboratory of Social Computing and Cognitive Intelligence, Dalian, LiaoNing, China"],"raw_orcid":"https://orcid.org/0000-0002-5557-7515","affiliations":[{"raw_affiliation_string":"Dalian University of Technology &amp; Ministry of Education, Key Laboratory of Social Computing and Cognitive Intelligence, Dalian, LiaoNing, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":["Dalian University of Technology, Dalian, LiaoNing, China"],"raw_orcid":"https://orcid.org/0000-0003-0872-7688","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, LiaoNing, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7298","last_page":"7306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"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":0.9901999831199646,"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":0.9815999865531921,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/storytelling","display_name":"Storytelling","score":0.759702205657959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5241249203681946},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3432881832122803},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.14253804087638855},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.12938359379768372},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.07738763093948364}],"concepts":[{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.759702205657959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241249203681946},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3432881832122803},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.14253804087638855},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.12938359379768372},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.07738763093948364}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1915485278","https://openalex.org/W1956340063","https://openalex.org/W2108598243","https://openalex.org/W2336525064","https://openalex.org/W2946794439","https://openalex.org/W2962858109","https://openalex.org/W2963989815","https://openalex.org/W3010694149","https://openalex.org/W3082665562","https://openalex.org/W3134095442","https://openalex.org/W3164024107","https://openalex.org/W4230405732","https://openalex.org/W4386076522","https://openalex.org/W4390873298","https://openalex.org/W4390874161","https://openalex.org/W4402753899"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2884441370","https://openalex.org/W1536421369","https://openalex.org/W2086118318","https://openalex.org/W2082193010","https://openalex.org/W4319988281","https://openalex.org/W2993120730","https://openalex.org/W1765898938"],"abstract_inverted_index":{"By":[0],"integrating":[1],"various":[2],"modules":[3],"with":[4],"the":[5,28,34,51,62,68,77,89,99,145],"Visual":[6],"Transformer":[7],"(ViT),":[8],"we":[9],"facilitate":[10],"a":[11,37,48,109,133],"interpretation":[12],"of":[13,39,50,106,123,136,149],"image":[14],"processing":[15],"across":[16,33],"each":[17,54],"layer":[18,55],"and":[19,32,56,65,121,147],"attention":[20,57,113],"head.":[21],"This":[22,71],"method":[23],"allows":[24],"us":[25],"to":[26,87,94,102],"explore":[27],"connections":[29],"both":[30],"within":[31,67,140],"layers,":[35,116],"enabling":[36,118],"analysis":[38,49],"how":[40],"images":[41],"are":[42],"processed":[43],"at":[44],"different":[45],"layers.":[46,70],"Conducting":[47],"contributions":[52],"from":[53,91],"head,":[58],"shedding":[59],"light":[60],"on":[61],"intricate":[63],"interactions":[64],"functionalities":[66],"model's":[69,100],"in-depth":[72],"exploration":[73],"not":[74],"only":[75],"highlights":[76],"visual":[78],"cues":[79],"between":[80,115],"layers":[81],"but":[82],"also":[83],"examines":[84],"their":[85],"capacity":[86],"navigate":[88],"transition":[90],"abstract":[92],"concepts":[93],"tangible":[95],"objects.":[96],"It":[97],"unveils":[98],"mechanism":[101],"building":[103],"an":[104],"understanding":[105,135],"images,":[107],"providing":[108],"strategy":[110],"for":[111,125,144],"adjusting":[112],"heads":[114],"thus":[117],"targeted":[119],"pruning":[120],"enhancement":[122,148],"performance":[124],"specific":[126],"tasks.":[127],"Our":[128],"research":[129],"indicates":[130],"that":[131],"achieving":[132],"scalable":[134],"transformer":[137],"models":[138],"is":[139],"reach,":[141],"offering":[142],"ways":[143],"refinement":[146],"such":[150],"models.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
