{"id":"https://openalex.org/W4405755066","doi":"https://doi.org/10.1109/tmm.2024.3521825","title":"Implicit and Explicit Language Guidance for Diffusion-Based Visual Perception","display_name":"Implicit and Explicit Language Guidance for Diffusion-Based Visual Perception","publication_year":2024,"publication_date":"2024-12-24","ids":{"openalex":"https://openalex.org/W4405755066","doi":"https://doi.org/10.1109/tmm.2024.3521825"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521825","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5027831564","display_name":"Hefeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hefeng Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-5330-5957","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-5160-6841","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin Xie","orcid":"https://orcid.org/0000-0001-6978-8834"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["School of Big Data and Software Engineering, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-6978-8834","affiliations":[{"raw_affiliation_string":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012919056","display_name":"Aiping Yang","orcid":"https://orcid.org/0000-0002-4469-2702"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiping Yang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6670-3727","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"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":0.22245482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"466","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9448000192642212,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9448000192642212,"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":0.8526222705841064},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.527075469493866},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4706755578517914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4447095990180969},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.41881227493286133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40151476860046387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36610913276672363},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3277534246444702},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09605434536933899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526222705841064},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.527075469493866},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4706755578517914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4447095990180969},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41881227493286133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40151476860046387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36610913276672363},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3277534246444702},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09605434536933899},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521825","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2199262417","display_name":null,"funder_award_id":"62206031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5074938571","display_name":null,"funder_award_id":"62271346","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G992463202","display_name":null,"funder_award_id":"62071323","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1903029394","https://openalex.org/W2412782625","https://openalex.org/W2630837129","https://openalex.org/W2737258237","https://openalex.org/W2894299524","https://openalex.org/W2955058313","https://openalex.org/W2964014680","https://openalex.org/W2981689412","https://openalex.org/W2990946490","https://openalex.org/W3014318259","https://openalex.org/W3014641072","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3165745140","https://openalex.org/W3170841864","https://openalex.org/W3173727695","https://openalex.org/W3174458495","https://openalex.org/W4214520160","https://openalex.org/W4214893857","https://openalex.org/W4226058394","https://openalex.org/W4312349930","https://openalex.org/W4312443924","https://openalex.org/W4312460030","https://openalex.org/W4312726009","https://openalex.org/W4312819733","https://openalex.org/W4312933868","https://openalex.org/W4319300976","https://openalex.org/W4322616103","https://openalex.org/W4386065386","https://openalex.org/W4386075819","https://openalex.org/W4386076222","https://openalex.org/W4386973803","https://openalex.org/W4388756695","https://openalex.org/W4390590999","https://openalex.org/W4390872147","https://openalex.org/W4390872705","https://openalex.org/W4390873429","https://openalex.org/W4390873622","https://openalex.org/W4390873752","https://openalex.org/W4392902551","https://openalex.org/W4402727668","https://openalex.org/W6685261749","https://openalex.org/W6739696289","https://openalex.org/W6766261854","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6791353385","https://openalex.org/W6797399245","https://openalex.org/W6802010497","https://openalex.org/W6804703708","https://openalex.org/W6805547681","https://openalex.org/W6809885388","https://openalex.org/W6811013733","https://openalex.org/W6811424244","https://openalex.org/W6838327568","https://openalex.org/W6838393215","https://openalex.org/W6838639034","https://openalex.org/W6839643428","https://openalex.org/W6842806116","https://openalex.org/W6846007759","https://openalex.org/W6849177959","https://openalex.org/W6857642668"],"related_works":["https://openalex.org/W4231937131","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W1480341462","https://openalex.org/W598950423","https://openalex.org/W4256673449","https://openalex.org/W4292559016","https://openalex.org/W2143331802"],"abstract_inverted_index":{"Text-to-image":[0],"diffusion":[1,15,36,97,121,129],"models":[2,16,37],"have":[3],"shown":[4],"powerful":[5],"ability":[6],"on":[7,173,189,206],"conditional":[8],"image":[9,84],"synthesis.":[10],"With":[11],"large-scale":[12],"vision-language":[13],"pre-training,":[14],"are":[17,93,171],"able":[18],"to":[19,86,95,116],"generate":[20,88],"high-quality":[21],"images":[22,112],"with":[23,228],"rich":[24],"textures":[25],"and":[26,52,71,145,181],"reasonable":[27],"structures":[28],"under":[29],"different":[30],"text":[31,90,101,114],"prompts.":[32,102],"However,":[33],"adapting":[34],"pre-trained":[35],"for":[38,57,160],"visual":[39,59],"perception":[40,176],"is":[41],"an":[42,50,66,72],"open":[43],"problem.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,125,155],"propose":[49],"implicit":[51,67,78,89,144,158],"explicit":[53,73,100,104,146],"language":[54,68,74],"guidance":[55,69,75],"framework":[56],"diffusion-based":[58],"perception,":[60],"named":[61],"IEDP.":[62],"Our":[63,184],"IEDP":[64,185,196,222],"comprises":[65],"branch":[70,79,105,159],"branch.":[76],"The":[77,103],"employs":[80],"a":[81,141,229],"frozen":[82],"CLIP":[83],"encoder":[85],"directly":[87],"embeddings":[91],"that":[92],"fed":[94],"the":[96,107,128,133,143,198,212,224],"model":[98,130,134],"without":[99],"uses":[106],"ground-truth":[108,168],"labels":[109],"of":[110,136,204,232],"corresponding":[111],"as":[113],"prompts":[115],"condition":[117],"feature":[118,151],"extraction":[119],"in":[120],"model.":[122],"During":[123,153],"training,":[124],"jointly":[126,149],"train":[127],"by":[131,216],"sharing":[132],"weights":[135],"these":[137],"two":[138,174],"branches.":[139],"As":[140],"result,":[142],"branches":[147],"can":[148],"guide":[150],"learning.":[152],"inference,":[154],"employ":[156],"only":[157],"final":[161],"prediction,":[162],"which":[163,210],"does":[164],"not":[165],"require":[166],"any":[167],"labels.":[169],"Experiments":[170],"performed":[172],"typical":[175],"tasks,":[177],"including":[178],"semantic":[179,193],"segmentation":[180],"depth":[182,219],"estimation.":[183],"achieves":[186],"promising":[187],"performance":[188],"both":[190],"tasks.":[191],"For":[192,218],"segmentation,":[194],"our":[195,221],"has":[197],"mIoU<inline-formula":[199],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[200],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[201],"notation=\"LaTeX\">$^\\text{ss}$</tex-math></inline-formula>":[202],"score":[203],"55.9%":[205],"ADE20K":[207],"validation":[208],"set,":[209],"outperforms":[211,223],"baseline":[213,225],"method":[214,226],"VPD":[215,227],"2.2%.":[217],"estimation,":[220],"relative":[230],"gain":[231],"11.0%.":[233]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}