{"id":"https://openalex.org/W4408356764","doi":"https://doi.org/10.1109/icassp49660.2025.10888875","title":"VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection","display_name":"VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356764","doi":"https://doi.org/10.1109/icassp49660.2025.10888875"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104470418","display_name":"Bin Zhang","orcid":"https://orcid.org/0009-0002-3710-2046"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics,Wuhan,China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038057515","display_name":"Guokuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guokuan Li","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics,Wuhan,China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044866795","display_name":"Jiguang Wan","orcid":"https://orcid.org/0000-0003-3440-4460"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiguang Wan","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics,Wuhan,China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9866999983787537,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9866999983787537,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9839000105857849,"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387596368789673},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6585909724235535},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5992279648780823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5676147937774658},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5593344569206238},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4416591227054596},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3831622302532196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24941477179527283},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08932116627693176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387596368789673},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6585909724235535},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5992279648780823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676147937774658},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5593344569206238},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4416591227054596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3831622302532196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24941477179527283},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08932116627693176},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2948982773","https://openalex.org/W2963149653","https://openalex.org/W2963611739","https://openalex.org/W2964248288","https://openalex.org/W3009436130","https://openalex.org/W3034230713","https://openalex.org/W3035564946","https://openalex.org/W3197733821","https://openalex.org/W3209445167","https://openalex.org/W4236889055","https://openalex.org/W4283819124","https://openalex.org/W4288083516","https://openalex.org/W4309279743","https://openalex.org/W4312776478","https://openalex.org/W4387490603","https://openalex.org/W4390872222","https://openalex.org/W4390873118","https://openalex.org/W4402713111","https://openalex.org/W6718836005","https://openalex.org/W6728622933","https://openalex.org/W6739651123","https://openalex.org/W6745891213","https://openalex.org/W6752760542","https://openalex.org/W6779395778","https://openalex.org/W6780874654","https://openalex.org/W6784323503","https://openalex.org/W6784333009","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6809902071","https://openalex.org/W6810300553","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"As":[0],"object":[1],"detectors":[2,39],"are":[3],"increasingly":[4],"deployed":[5],"as":[6],"black-box":[7],"cloud":[8],"services":[9],"or":[10],"pre-trained":[11,54],"models":[12,56,62],"with":[13],"restricted":[14],"access":[15],"to":[16,63,70,100,118],"the":[17,21,36,71,116],"original":[18],"training":[19],"data,":[20],"challenge":[22],"of":[23,38,73],"zero-shot":[24,104],"object-level":[25,64,105],"out-of-distribution":[26],"(OOD)":[27],"detection":[28,52,66],"arises.":[29],"This":[30],"task":[31],"becomes":[32],"crucial":[33],"in":[34,40,49],"ensuring":[35],"reliability":[37],"open-world":[41],"settings.":[42],"While":[43],"existing":[44],"methods":[45],"have":[46],"demonstrated":[47],"success":[48],"image-level":[50,79],"OOD":[51,65,106,123],"using":[53],"vision-language":[55],"like":[57],"CLIP,":[58],"directly":[59],"applying":[60],"such":[61],"presents":[67],"challenges":[68],"due":[69],"loss":[72],"contextual":[74,112],"information":[75,113],"and":[76,94,114,122],"reliance":[77],"on":[78],"alignment.":[80],"To":[81],"tackle":[82],"these":[83],"challenges,":[84],"we":[85],"introduce":[86],"a":[87],"new":[88],"method":[89,109],"that":[90],"leverages":[91],"visual":[92],"prompts":[93],"text-augmented":[95],"in-distribution":[96],"(ID)":[97],"space":[98],"construction":[99],"adapt":[101],"CLIP":[102],"for":[103],"detection.":[107],"Our":[108],"preserves":[110],"critical":[111],"improves":[115],"ability":[117],"differentiate":[119],"between":[120],"ID":[121],"objects,":[124],"achieving":[125],"competitive":[126],"performance":[127],"across":[128],"different":[129],"benchmarks.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}