{"id":"https://openalex.org/W4415537031","doi":"https://doi.org/10.1145/3746027.3755017","title":"Towards Universal Perception through Language-Guided Open-World Object Detection","display_name":"Towards Universal Perception through Language-Guided Open-World Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537031","doi":"https://doi.org/10.1145/3746027.3755017"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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":null,"display_name":"Zihan Wang","orcid":"https://orcid.org/0009-0000-1026-6476"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-1026-6476","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039883116","display_name":"Yunhang Shen","orcid":"https://orcid.org/0000-0002-3970-7519"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhang Shen","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3970-7519","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108978349","display_name":"Yuan Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Fang","raw_affiliation_strings":["East China Normal University, Shanghai, China and The 27th Research Institute of CETC, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-4899-7677","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China and The 27th Research Institute of CETC, Zhengzhou, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115731913","display_name":"Zuwei Long","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuwei Long","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-3827-2243","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725160","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-7998-0731"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7998-0731","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004402130","display_name":"Xing Sun","orcid":"https://orcid.org/0000-0001-8132-9083"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Sun","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8132-9083","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934124","display_name":"Jiao Xie","orcid":"https://orcid.org/0000-0002-1488-2118"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Xie","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1488-2118","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043643513","display_name":"Shaohui Lin","orcid":"https://orcid.org/0000-0003-0284-9940"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Lin","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0284-9940","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28632111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1190","last_page":"1199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/object-detection","display_name":"Object detection","score":0.7329999804496765},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5763999819755554},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5375000238418579},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5339999794960022},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.503600001335144},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.492900013923645},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3921999931335449},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800999879837036},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7329999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6952000260353088},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3921999931335449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2912999987602234},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5437778857","display_name":null,"funder_award_id":"62102151","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6269048073","display_name":null,"funder_award_id":"2024M760930","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2962766617","https://openalex.org/W3096609285","https://openalex.org/W4288083516","https://openalex.org/W4312424618","https://openalex.org/W4312960937"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,62,70,173],"detection":[2,12,71,174],"seeks":[3],"to":[4,92,121,137],"recognize":[5],"objects":[6,81],"from":[7],"arbitrary":[8],"language":[9,103,130],"inputs,":[10],"extending":[11],"beyond":[13],"fixed":[14],"training":[15,153],"categories.":[16],"While":[17],"recent":[18],"methods":[19,205],"have":[20],"made":[21],"progress":[22],"in":[23,42,82],"detecting":[24],"unseen":[25],"categories,":[26],"they":[27],"typically":[28],"require":[29],"a":[30,54,93,112,129,150,210],"set":[31],"of":[32,76,85,96],"predefined":[33,86],"categories":[34],"during":[35],"the":[36,83,102,202],"inference":[37],"stage,":[38],"hindering":[39],"practical":[40],"deployment":[41],"open-world":[43,196],"scenarios.":[44],"To":[45],"overcome":[46],"this":[47],"crucial":[48],"limitation,":[49],"we":[50],"propose":[51],"UniPerception":[52,105,193],",":[53],"novel":[55],"universal":[56],"perception":[57,213],"framework":[58],"based":[59],"on":[60,117,145,168],"open-vocabulary":[61,69,172],"detection.":[63],"It":[64],"not":[65],"only":[66],"excels":[67],"at":[68],"but":[72],"is":[73],"also":[74],"capable":[75],"generating":[77],"labels":[78],"for":[79,171],"target":[80],"absence":[84],"vocabularies,":[87],"and":[88,124,140,148,183,198,206],"can":[89],"be":[90],"adapted":[91],"broad":[94],"range":[95],"vision-language":[97,162,184],"tasks":[98],"simply":[99],"by":[100],"modifying":[101],"instructions.":[104],"seamlessly":[106],"integrates":[107],"three":[108],"key":[109],"innovations:":[110],"1)":[111],"robust":[113],"visual":[114,126,146],"detector":[115],"trained":[116],"diverse":[118],"data":[119],"sources":[120],"capture":[122],"rich":[123],"generalizable":[125],"representations;":[127],"2)":[128],"model":[131],"with":[132,160],"interleaved":[133],"cross-modality":[134],"fusion":[135],"layers":[136],"interpret":[138],"instructions":[139],"generate":[141],"fine-grained":[142],"responses":[143],"conditioned":[144],"features;":[147],"3)":[149],"tailored":[151],"multi-stage":[152],"strategy":[154],"that":[155,192],"effectively":[156],"bridges":[157],"detection-specific":[158],"learning":[159],"general":[161],"understanding.":[163],"We":[164],"conduct":[165],"extensive":[166],"experiments":[167],"multiple":[169],"benchmarks":[170],"(COCO,":[175],"LVIS,":[176],"ODinW),":[177],"referring":[178],"expression":[179],"comprehension":[180],"(RefCOCO/+/g,":[181],"D3),":[182],"understanding":[185],"(Flickr30k,":[186],"VQAv2,":[187],"GQA).":[188],"The":[189],"results":[190],"show":[191],"achieves":[194],"strong":[195],"generalization":[197],"multi-modal":[199],"understanding,":[200],"outperforming":[201],"existing":[203],"state-of-the-art":[204],"establishing":[207],"itself":[208],"as":[209],"unified,":[211],"instruction-driven":[212],"system.":[214]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}