{"id":"https://openalex.org/W4415540446","doi":"https://doi.org/10.1145/3746027.3754727","title":"Chain-of-Cooking: Cooking Process Visualization via Bidirectional Chain-of-Thought Guidance","display_name":"Chain-of-Cooking: Cooking Process Visualization via Bidirectional Chain-of-Thought Guidance","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540446","doi":"https://doi.org/10.1145/3746027.3754727"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754727","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.21529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076639787","display_name":"Mengling Xu","orcid":"https://orcid.org/0009-0002-4809-9129"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengling Xu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-4809-9129","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776884","display_name":"Ming Tao","orcid":"https://orcid.org/0000-0002-4662-7170"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4662-7170","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"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":"9287","last_page":"9295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9704999923706055,"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":0.9704999923706055,"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/visualization","display_name":"Visualization","score":0.7827000021934509},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6620000004768372},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6175000071525574},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5519000291824341},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4796999990940094},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7827000021934509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769599974155426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6620000004768372},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056999921798706},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C3017437641","wikidata":"https://www.wikidata.org/wiki/Q38695","display_name":"Cooking methods","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754727","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"},{"id":"pmh:oai:arXiv.org:2507.21529","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.21529","pdf_url":"https://arxiv.org/pdf/2507.21529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.21529","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.21529","pdf_url":"https://arxiv.org/pdf/2507.21529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","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":12,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W2741230247","https://openalex.org/W3034667500","https://openalex.org/W3081217025","https://openalex.org/W3093100367","https://openalex.org/W3159481202","https://openalex.org/W4312443924","https://openalex.org/W4312933868","https://openalex.org/W4386065512","https://openalex.org/W4386076676","https://openalex.org/W4386437562","https://openalex.org/W4402774246"],"related_works":[],"abstract_inverted_index":{"Cooking":[0],"process":[1,115],"visualization":[2,116],"is":[3,65,96],"a":[4,27,113,129,165,170,228],"promising":[5],"task":[6],"in":[7,49,105,252],"the":[8,42,51,55,69,76,84,90,100,153,157,178,183,188,202,206,210,215,222,238],"intersection":[9],"of":[10,26,37,57,72,92,103,125,160,180,233],"image":[11,21,138],"generation":[12],"and":[13,45,155,169,194,198,242,255],"food":[14],"analysis,":[15],"which":[16,142],"aims":[17],"to":[18,67,80,98,121,134,146,151,213],"generate":[19,68,122],"an":[20],"for":[22,237],"each":[23],"cooking":[24,52,62,114,196,217,239,258],"step":[25,86,218],"recipe.":[28],"However,":[29],"most":[30,144],"existing":[31,250],"works":[32],"focus":[33],"on":[34,41,89],"generating":[35,253],"images":[36,104],"finished":[38],"foods":[39,73],"based":[40],"given":[43],"recipes,":[44],"face":[46],"two":[47],"challenges":[48],"visualizing":[50],"process.":[53,240,259],"First,":[54],"appearance":[56],"ingredients":[58],"changes":[59],"variously":[60],"across":[61],"steps,":[63],"it":[64,95,200],"difficult":[66],"correct":[70,123],"appearances":[71,124],"that":[74,246],"match":[75],"textual":[77,148],"description,":[78],"leading":[79],"semantic":[81,256],"inconsistency.":[82],"Second,":[83],"current":[85,147,195,216],"might":[87],"depend":[88],"operations":[91],"previous":[93,181,223],"step,":[94,197],"crucial":[97],"maintain":[99],"contextual":[101],"coherence":[102,154],"sequential":[106],"order.":[107],"In":[108],"this":[109],"work,":[110],"we":[111,127,163,226],"present":[112,128],"model,":[117],"called":[118],"Chain-of-Cooking.":[119],"Specifically,":[120],"ingredients,":[126],"Dynamic":[130],"Patch":[131],"Selection":[132],"Module":[133,168,186],"retrieve":[135],"previously":[136],"generated":[137,161],"patches":[139],"as":[140],"references,":[141],"are":[143],"related":[145],"contents.":[149],"Furthermore,":[150],"enhance":[152],"keep":[156],"rational":[158],"order":[159],"images,":[162],"propose":[164],"Semantic":[166,184],"Evolution":[167,185],"Bidirectional":[171],"Chain-of-Thought":[172],"(CoT)":[173],"Guidance.":[174],"To":[175],"better":[176],"utilize":[177],"semantics":[179],"texts,":[182],"establishes":[187],"semantical":[189],"association":[190],"between":[191],"latent":[192,203],"prompts":[193],"merges":[199],"with":[201,221],"features.":[204],"Then":[205],"CoT":[207],"Guidance":[208],"updates":[209],"merged":[211],"features":[212],"guide":[214],"remain":[219],"coherent":[220,254],"step.":[224],"Moreover,":[225],"construct":[227],"dataset":[229],"named":[230],"CookViz,":[231],"consisting":[232],"intermediate":[234],"image-text":[235],"pairs":[236],"Quantitative":[241],"qualitative":[243],"experiments":[244],"show":[245],"our":[247],"method":[248],"outperforms":[249],"methods":[251],"consistent":[257]},"counts_by_year":[],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}