{"id":"https://openalex.org/W4405934235","doi":"https://doi.org/10.1109/tcsvt.2024.3524784","title":"FocusCLIP: Focusing on Anomaly Regions by Visual-Text Discrepancies","display_name":"FocusCLIP: Focusing on Anomaly Regions by Visual-Text Discrepancies","publication_year":2024,"publication_date":"2024-12-31","ids":{"openalex":"https://openalex.org/W4405934235","doi":"https://doi.org/10.1109/tcsvt.2024.3524784"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3524784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3524784","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/A5101056085","display_name":"Yuan Zhao","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":"Yuan Zhao","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3723-1024","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080125156","display_name":"Jiayu Sun","orcid":"https://orcid.org/0000-0003-3070-7501"},"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":"Jiayu Sun","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3070-7501","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015500789","display_name":"Lihe Zhang","orcid":"https://orcid.org/0000-0002-9241-1688"},"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":"Lihe Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-9241-1688","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"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":"Huchuan Lu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2732,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94738999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"35","issue":"5","first_page":"4883","last_page":"4895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5615691542625427},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4474336504936218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43864548206329346},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3842203617095947},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12975823879241943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5615691542625427},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4474336504936218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43864548206329346},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3842203617095947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12975823879241943},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3524784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3524784","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":[],"awards":[{"id":"https://openalex.org/G2743260224","display_name":null,"funder_award_id":"2023JJ12GX015","funder_id":"https://openalex.org/F4320336584","funder_display_name":"Dalian Science and Technology Innovation Fund"},{"id":"https://openalex.org/G3064143480","display_name":null,"funder_award_id":"62431004","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"},{"id":"https://openalex.org/F4320336584","display_name":"Dalian Science and Technology Innovation Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2295107390","https://openalex.org/W2765793020","https://openalex.org/W2948982773","https://openalex.org/W2962858109","https://openalex.org/W2964137095","https://openalex.org/W3034314048","https://openalex.org/W3106848223","https://openalex.org/W3118895125","https://openalex.org/W3147184966","https://openalex.org/W3159879667","https://openalex.org/W3169651898","https://openalex.org/W4212874935","https://openalex.org/W4312298392","https://openalex.org/W4312570668","https://openalex.org/W4312605624","https://openalex.org/W4312772600","https://openalex.org/W4313153210","https://openalex.org/W4316660730","https://openalex.org/W4386065385","https://openalex.org/W4386065890","https://openalex.org/W4386071798","https://openalex.org/W4386075561","https://openalex.org/W4386075649","https://openalex.org/W4386075837","https://openalex.org/W4388266117","https://openalex.org/W4390871926","https://openalex.org/W4390872445","https://openalex.org/W4390872497","https://openalex.org/W4390872570","https://openalex.org/W4390872785","https://openalex.org/W4390873025","https://openalex.org/W4390874124","https://openalex.org/W4391168247","https://openalex.org/W4393158476","https://openalex.org/W4393241214","https://openalex.org/W4394625837","https://openalex.org/W4394785917","https://openalex.org/W4400111402","https://openalex.org/W4400409509","https://openalex.org/W4402733578","https://openalex.org/W6777869702","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6802987763","https://openalex.org/W6846007759","https://openalex.org/W6858057904","https://openalex.org/W6860959701"],"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":{"Few-shot":[0],"anomaly":[1,118,188,202],"detection":[2],"aims":[3],"to":[4,49,85,100,137,165],"detect":[5,50,141],"defects":[6,28],"with":[7],"only":[8],"a":[9,68,72],"limited":[10],"number":[11],"of":[12,67,92,208],"normal":[13],"samples":[14],"for":[15],"training.":[16],"Recent":[17],"few-shot":[18,187],"methods":[19,185],"typically":[20],"focus":[21],"on":[22,37,177],"object-level":[23,44],"features":[24,45,139],"rather":[25],"than":[26],"subtle":[27],"within":[29,194],"objects,":[30],"as":[31],"pretrained":[32],"models":[33],"are":[34,46,53],"generally":[35],"trained":[36],"classification":[38],"or":[39],"image-text":[40],"matching":[41],"datasets.":[42],"However,":[43],"often":[47],"insufficient":[48],"defects,":[51],"which":[52,65,116],"characterized":[54],"by":[55,145],"fine-grained":[56,90],"texture":[57],"variations.":[58],"To":[59],"address":[60],"this,":[61],"we":[62,96,108],"propose":[63,109],"FocusCLIP,":[64],"consists":[66],"vision-guided":[69,106],"branch":[70,193],"and":[71,82,123,140,174],"language-guided":[73,154,192],"branch.":[74],"FocusCLIP":[75,195],"leverages":[76],"the":[77,105,110,130,153,183,191,206],"complementary":[78],"relationship":[79],"between":[80],"visual":[81],"text":[83,167],"modalities":[84],"jointly":[86],"emphasize":[87],"discrepancies":[88],"in":[89,186,200],"textures":[91],"defect":[93,178],"regions.":[94,179],"Specifically,":[95],"design":[97],"three":[98],"modules":[99],"mine":[101],"these":[102,125],"discrepancies.":[103,126],"In":[104,152],"branch,":[107,155],"Bidirectional":[111],"Self-knowledge":[112],"Distillation":[113],"(BSD)":[114],"structure,":[115,129],"identifies":[117],"regions":[119,173],"through":[120],"inconsistent":[121],"representations":[122],"accumulates":[124],"Within":[127],"this":[128],"Anomaly":[131],"Capture":[132],"Module":[133],"(ACM)":[134],"is":[135],"designed":[136],"refine":[138],"more":[142],"comprehensive":[143],"anomalies":[144],"leveraging":[146],"semantic":[147],"cues":[148],"from":[149,171],"multi-head":[150],"self-attention.":[151],"Multi-level":[156],"Adversarial":[157],"Class":[158],"Activation":[159],"Mapping":[160],"(MACAM)":[161],"utilizes":[162],"foreground-invariant":[163],"responses":[164],"adversarial":[166],"prompts,":[168],"reducing":[169],"interference":[170],"object":[172],"further":[175,204],"focusing":[176],"Our":[180],"approach":[181],"outperforms":[182],"state-of-the-art":[184],"detection.":[189],"Additionally,":[190],"also":[196],"demonstrates":[197],"competitive":[198],"performance":[199],"zero-shot":[201],"detection,":[203],"validating":[205],"effectiveness":[207],"our":[209],"proposed":[210],"method.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}