{"id":"https://openalex.org/W7137945967","doi":"https://doi.org/10.1609/aaai.v40i14.38191","title":"Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment","display_name":"Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137945967","doi":"https://doi.org/10.1609/aaai.v40i14.38191"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38191","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38191","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i14.38191","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125642588","display_name":"Wenti Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenti Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733420","display_name":"Huaxin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaxin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129676983","display_name":"Xiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723843","display_name":"Yuqing Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuqing Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129640816","display_name":"Yicheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicheng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125704420","display_name":"Bingquan Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingquan Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697310","display_name":"Jialong Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialong Zuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700875","display_name":"Li Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669724","display_name":"Changxin Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changxin Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112116313","display_name":"Nong Sang","orcid":"https://orcid.org/0000-0003-2736-3920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nong Sang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.531,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95156695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"40","issue":"14","first_page":"12027","last_page":"12035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.955299973487854,"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":0.955299973487854,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.027300000190734863,"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":0.005499999970197678,"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/anomaly-detection","display_name":"Anomaly detection","score":0.642300009727478},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.579800009727478},{"id":"https://openalex.org/keywords/normality","display_name":"Normality","score":0.542900025844574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47369998693466187},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3953000009059906},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.3637000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7019000053405762},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.642300009727478},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.542900025844574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38191","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38191","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38191","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38191","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7010391354560852}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,128],"weakly-supervised":[3],"video":[4,111,159],"anomaly":[5,167],"detection":[6],"have":[7],"achieved":[8],"remarkable":[9],"performance":[10],"by":[11],"applying":[12],"the":[13,40,94,98,114,121,129,133,143],"multiple":[14],"instance":[15],"learning":[16,174],"paradigm":[17],"based":[18],"on":[19,181],"multimodal":[20],"foundation":[21],"models":[22],"such":[23],"as":[24],"CLIP":[25],"to":[26,38,47,58,62,66,81,123,175],"highlight":[27],"anomalous":[28,140],"instances":[29],"and":[30,55,85,90,139,162,169,187],"classify":[31],"categories.":[32],"However,":[33],"their":[34],"objectives":[35],"may":[36],"tend":[37],"detect":[39],"most":[41],"salient":[42],"response":[43],"segments,":[44],"while":[45],"neglecting":[46],"mine":[48],"diverse":[49],"normal":[50,86,118,137],"patterns":[51,138],"separated":[52],"from":[53,88],"anomalies,":[54],"are":[56],"prone":[57],"category":[59],"confusion":[60],"due":[61],"similar":[63],"appearance,":[64],"leading":[65],"unsatisfactory":[67],"fine-grained":[68,91,144],"classification":[69],"results.":[70],"Therefore,":[71],"we":[72,101,146],"propose":[73],"a":[74,103,148],"novel":[75],"Disentangled":[76],"Semantic":[77],"Alignment":[78],"Network":[79],"(DSANet)":[80],"explicitly":[82],"separate":[83],"abnormal":[84],"features":[87,112],"coarse-grained":[89,99],"aspects,":[92],"enhancing":[93],"distinguishability.":[95],"Specifically,":[96],"at":[97],"level,":[100,145],"introduce":[102],"self-guided":[104],"normality":[105,125],"modeling":[106],"branch":[107],"that":[108,190],"reconstructs":[109],"input":[110],"under":[113],"guidance":[115],"of":[116,136],"learned":[117],"prototypes,":[119],"encouraging":[120],"model":[122],"exploit":[124],"cues":[126],"inherent":[127],"video,":[130],"thereby":[131],"improving":[132],"temporal":[134],"separation":[135],"events.":[141],"At":[142],"present":[147],"decoupled":[149],"contrastive":[150,173],"semantic":[151],"alignment":[152],"mechanism,":[153],"which":[154],"first":[155],"temporally":[156],"decomposes":[157],"each":[158],"into":[160],"event-centric":[161],"background-centric":[163],"components":[164],"using":[165],"frame-level":[166],"scores":[168],"then":[170],"applies":[171],"visual-language":[172],"enhance":[176],"class-discriminative":[177],"representations.":[178],"Comprehensive":[179],"experiments":[180],"two":[182],"standard":[183],"benchmarks,":[184],"namely":[185],"XD-Violence":[186],"UCF-Crime,":[188],"demonstrate":[189],"DSANet":[191],"outperforms":[192],"existing":[193],"state-of-the-art":[194],"methods.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2026-03-18T00:00:00"}