{"id":"https://openalex.org/W4405779000","doi":"https://doi.org/10.1109/tmm.2024.3521813","title":"Improving Vision Anomaly Detection With the Guidance of Language Modality","display_name":"Improving Vision Anomaly Detection With the Guidance of Language Modality","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405779000","doi":"https://doi.org/10.1109/tmm.2024.3521813"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521813","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/A5091714064","display_name":"Dong Chen","orcid":"https://orcid.org/0000-0002-4859-1757"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Chen","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4859-1757","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033407215","display_name":"Kaihang Pan","orcid":"https://orcid.org/0009-0001-2967-4573"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaihang Pan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guangyu Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Dai","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101477058","display_name":"Guoming Wang","orcid":"https://orcid.org/0000-0003-3131-6916"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoming Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3131-6916","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759885","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-7361-3084"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7361-3084","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7356-9711","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081346568","display_name":"Mingliang Xu","orcid":"https://orcid.org/0000-0002-6885-3451"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Xu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6885-3451","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091714064"],"corresponding_institution_ids":["https://openalex.org/I38877650","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2145359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1410","last_page":"1419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.660099983215332,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.660099983215332,"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/computer-science","display_name":"Computer science","score":0.8016954660415649},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6592873334884644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463718175888062},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5266756415367126},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44332340359687805},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.396058589220047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016954660415649},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6592873334884644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463718175888062},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5266756415367126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44332340359687805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.396058589220047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521813","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G1781607827","display_name":null,"funder_award_id":"62272411","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":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1876967670","https://openalex.org/W2053186076","https://openalex.org/W2106277773","https://openalex.org/W2194775991","https://openalex.org/W2510520237","https://openalex.org/W2558393669","https://openalex.org/W2605997098","https://openalex.org/W2781891981","https://openalex.org/W2804483946","https://openalex.org/W2896457183","https://openalex.org/W2914570111","https://openalex.org/W2947805333","https://openalex.org/W2948982773","https://openalex.org/W3014352273","https://openalex.org/W3108027406","https://openalex.org/W3132936317","https://openalex.org/W3200038569","https://openalex.org/W4285293775","https://openalex.org/W4312245888","https://openalex.org/W4312274522","https://openalex.org/W4312871172","https://openalex.org/W6631190155","https://openalex.org/W6675108834","https://openalex.org/W6680970901","https://openalex.org/W6738348428","https://openalex.org/W6744798462","https://openalex.org/W6751494907","https://openalex.org/W6751866786","https://openalex.org/W6752910514","https://openalex.org/W6765696844","https://openalex.org/W6780191644","https://openalex.org/W6780874654","https://openalex.org/W6789731502","https://openalex.org/W6838931418","https://openalex.org/W6839494292","https://openalex.org/W6841299521"],"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":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"a":[4,62,128,140],"surge":[5],"of":[6,49,65,74,88,100,155,160,171,186],"interest":[7],"in":[8,40,162],"anomaly":[9,14,35,136],"detection.":[10],"However,":[11],"existing":[12],"unsupervised":[13],"detectors,":[15],"particularly":[16],"those":[17],"for":[18,58,133],"the":[19,41,46,50,55,86,101,106,110,120,134,145,149,153,163,169,172,178,184,197,200,210],"vision":[20,59,135],"modality,":[21],"face":[22],"significant":[23],"challenges":[24,57],"due":[25,44],"to":[26,45,84,118,157,177,212],"redundant":[27,89],"information":[28,90],"and":[29,79,91,104,203],"sparse":[30,92],"latent":[31,93,131,164],"space.":[32,165],"In":[33],"contrast,":[34],"detectors":[36],"demonstrate":[37,168],"superior":[38],"performance":[39,185],"language":[42,146],"modality":[43,60],"unimodal":[47],"nature":[48],"data.":[51],"This":[52],"paper":[53],"tackles":[54],"aforementioned":[56],"from":[61,144],"multimodal":[63],"point":[64],"view.":[66],"Specifically,":[67],"we":[68],"propose":[69],"Cross-modal":[70,75,80],"Guidance":[71],"(CMG),":[72],"comprising":[73],"Entropy":[76],"Reduction":[77],"(CMER)":[78],"Linear":[81],"Embedding":[82],"(CMLE),":[83],"address":[85],"issues":[87],"space,":[94],"respectively.":[95],"CMER":[96,114,202],"involves":[97],"masking":[98],"portions":[99],"raw":[102],"image":[103],"computing":[105],"matching":[107],"score":[108],"with":[109],"corresponding":[111],"text.":[112],"Essentially,":[113],"eliminates":[115],"irrelevant":[116],"pixels":[117],"direct":[119],"detector's":[121],"focus":[122],"towards":[123],"critical":[124],"content.":[125],"To":[126],"learn":[127],"more":[129],"compact":[130],"space":[132],"detection,":[137],"CMLE":[138],"learns":[139],"correlation":[141],"structure":[142],"matrix":[143,151],"modality.":[147],"Then,":[148],"acquired":[150],"compels":[152],"distribution":[154],"images":[156],"resemble":[158],"that":[159,180],"texts":[161],"Extensive":[166],"experiments":[167,194],"effectiveness":[170],"proposed":[173,201],"methods.":[174],"Particularly,":[175],"compared":[176],"baseline":[179],"only":[181],"utilizes":[182],"images,":[183],"CMG":[187],"has":[188],"been":[189],"improved":[190],"by":[191],"16.81%.":[192],"Ablation":[193],"further":[195],"confirm":[196],"synergy":[198],"among":[199],"CMLE,":[204],"as":[205],"each":[206],"component":[207],"depends":[208],"on":[209],"other":[211],"achieve":[213],"optimal":[214],"performance.":[215]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}