{"id":"https://openalex.org/W4416550159","doi":"https://doi.org/10.1145/3805622.3810583","title":"UniDGF: A Unified Detection-to-Generation Framework for Hierarchical Object Visual Recognition","display_name":"UniDGF: A Unified Detection-to-Generation Framework for Hierarchical Object Visual Recognition","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W4416550159","doi":"https://doi.org/10.1145/3805622.3810583"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810583","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810583","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086615023","display_name":"Xinyu Nan","orcid":"https://orcid.org/0009-0007-8245-2607"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Nan","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8245-2607","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059651249","display_name":"Lingtao Mao","orcid":"https://orcid.org/0000-0001-5872-9695"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingtao Mao","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-2804-5872","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111142513","display_name":"H.-F. Dai","orcid":"https://orcid.org/0000-0002-3844-8359"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huangyu Dai","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3844-8359","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086841075","display_name":"Zexin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexin Zheng","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-8043-5842","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101280318","display_name":"Xinyu Sun","orcid":"https://orcid.org/0009-0005-6223-0287"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Sun","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-5934-2652","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057994068","display_name":"Zihan Liang","orcid":"https://orcid.org/0009-0003-2373-1439"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Liang","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-2373-1439","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088723608","display_name":"Ben Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ben Chen","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4495-8686","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010036447","display_name":"Yuqing Ding","orcid":"https://orcid.org/0000-0002-8092-4646"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyi Lei","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6287-3673","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01083852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1583","last_page":"1587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39399999380111694,"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":0.39399999380111694,"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":0.22709999978542328,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.09870000183582306,"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/object","display_name":"Object (grammar)","score":0.609000027179718},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.560699999332428},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5386000275611877},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4948999881744385},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4902999997138977},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4174000024795532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141999959945679},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.560699999332428},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5386000275611877},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4902999997138977},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C75814411","wikidata":"https://www.wikidata.org/wiki/Q4818714","display_name":"Attribute domain","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3805622.3810583","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810583","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.15984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.15984","pdf_url":"https://arxiv.org/pdf/2511.15984","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.15984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.15984","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810583","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810583","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"visual":[1],"semantic":[2,75],"understanding":[3],"requires":[4],"a":[5,48,70,78],"unified":[6,123],"framework":[7,51],"that":[8,52,104],"simultaneously":[9],"handles":[10],"object":[11],"detection,":[12],"category":[13,31,55,82],"prediction,":[14],"and":[15,26,33,56,68,84,100,112,120],"attribute":[16,35,57,91],"recognition.":[17,92],"However,":[18],"current":[19],"advanced":[20],"approaches":[21],"rely":[22],"on":[23,94],"global":[24],"similarity":[25],"struggle":[27],"to":[28,73],"capture":[29],"fine-grained":[30,118],"distinctions":[32],"category-specific":[34],"diversity,":[36],"especially":[37],"in":[38,77],"large-scale":[39,96],"e-commerce":[40,98],"scenarios.":[41],"To":[42],"overcome":[43],"these":[44],"challenges,":[45],"we":[46,63],"introduce":[47],"detection-guided":[49],"generative":[50],"predicts":[53],"hierarchical":[54],"tokens.":[58],"For":[59],"each":[60],"detected":[61],"object,":[62],"extract":[64],"refined":[65],"ROI-level":[66],"features":[67],"employ":[69],"BART-based":[71],"generator":[72],"produce":[74],"tokens":[76],"coarse-to-fine":[79],"sequence":[80],"covering":[81],"hierarchies":[83],"property\u2013value":[85],"pairs,":[86],"with":[87],"support":[88],"for":[89],"property-conditioned":[90],"Experiments":[93],"both":[95],"proprietary":[97],"datasets":[99,102],"open-source":[101],"demonstrate":[103],"our":[105],"approach":[106],"significantly":[107],"outperforms":[108],"existing":[109],"similarity-based":[110],"pipelines":[111],"multi-stage":[113],"classification":[114],"systems,":[115],"achieving":[116],"stronger":[117],"recognition":[119],"more":[121],"coherent":[122],"inference.":[124]},"counts_by_year":[],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-11-23T00:00:00"}