{"id":"https://openalex.org/W4387968210","doi":"https://doi.org/10.1145/3581783.3611934","title":"Object Part Parsing with Hierarchical Dual Transformer","display_name":"Object Part Parsing with Hierarchical Dual Transformer","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968210","doi":"https://doi.org/10.1145/3581783.3611934"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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":"https://openalex.org/A5100687406","display_name":"Jiamin Chen","orcid":"https://orcid.org/0000-0002-4968-148X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiamin Chen","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-4968-148X","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079767760","display_name":"Jianlou Si","orcid":"https://orcid.org/0000-0002-2029-6588"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlou Si","raw_affiliation_strings":["SenseTime, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2029-6588","affiliations":[{"raw_affiliation_string":"SenseTime, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000850153","display_name":"Naihao Liu","orcid":"https://orcid.org/0000-0002-2609-7408"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naihao Liu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-2609-7408","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727989","display_name":"Yao Wu","orcid":"https://orcid.org/0000-0002-8585-283X"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Wu","raw_affiliation_strings":["SenseTime, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8585-283X","affiliations":[{"raw_affiliation_string":"SenseTime, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032618817","display_name":"Li Niu","orcid":"https://orcid.org/0000-0003-1970-8634"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Niu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1970-8634","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100657544","display_name":"Chen Qian","orcid":"https://orcid.org/0000-0002-8761-5563"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Qian","raw_affiliation_strings":["SenseTime, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8761-5563","affiliations":[{"raw_affiliation_string":"SenseTime, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100687406"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.1177,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42615698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2016","last_page":"2024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.9941999912261963,"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/parsing","display_name":"Parsing","score":0.8019206523895264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750749945640564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.577444851398468},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5583138465881348},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.5549538135528564},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.533092200756073},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5122007727622986},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.47797009348869324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.374106228351593},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.370911180973053},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3485097885131836},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3202897906303406},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16748496890068054}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8019206523895264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750749945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.577444851398468},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5583138465881348},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.5549538135528564},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.533092200756073},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5122007727622986},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.47797009348869324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.374106228351593},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.370911180973053},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3485097885131836},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3202897906303406},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16748496890068054},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W2104408738","https://openalex.org/W2295744361","https://openalex.org/W2560023338","https://openalex.org/W2791731612","https://openalex.org/W2886799640","https://openalex.org/W2916798096","https://openalex.org/W2964072977","https://openalex.org/W2979879857","https://openalex.org/W2991453701","https://openalex.org/W2997973210","https://openalex.org/W2998428583","https://openalex.org/W3034230284","https://openalex.org/W3034521057","https://openalex.org/W3034760601","https://openalex.org/W3035069238","https://openalex.org/W3035433720","https://openalex.org/W3043563192","https://openalex.org/W3094918035","https://openalex.org/W3096609285","https://openalex.org/W3107113572","https://openalex.org/W3109301572","https://openalex.org/W3110495309","https://openalex.org/W3112172934","https://openalex.org/W3129840128","https://openalex.org/W3138516171","https://openalex.org/W3159093935","https://openalex.org/W3166525903","https://openalex.org/W3168227666","https://openalex.org/W3170544306","https://openalex.org/W3170841864","https://openalex.org/W3171888599","https://openalex.org/W3180659539","https://openalex.org/W3186903169","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W3213792864","https://openalex.org/W4312376014","https://openalex.org/W4312689172","https://openalex.org/W4312815172"],"related_works":["https://openalex.org/W2251084681","https://openalex.org/W287510790","https://openalex.org/W2098784136","https://openalex.org/W2968543375","https://openalex.org/W2571817549","https://openalex.org/W1970099335","https://openalex.org/W1541975828","https://openalex.org/W2888625260","https://openalex.org/W2159336305","https://openalex.org/W3035970863"],"abstract_inverted_index":{"Object":[0],"part":[1,71,85,115,143,194],"parsing":[2,72],"involves":[3],"segmenting":[4],"objects":[5],"into":[6],"semantic":[7,76],"parts,":[8,162],"which":[9,26],"has":[10],"drawn":[11],"great":[12],"attention":[13],"recently.":[14],"The":[15,169],"current":[16],"methods":[17],"ignore":[18],"the":[19,24,39,46,49,54,60,66,69,96,99,114,122,125,138,142,147,157],"specific":[20],"hierarchical":[21,119,139],"structure":[22],"of":[23,48,53,68,98,124],"object,":[25],"can":[27],"be":[28],"used":[29],"as":[30],"strong":[31],"prior":[32],"knowledge.":[33],"To":[34],"address":[35],"this,":[36],"we":[37,106,130],"propose":[38,131],"Hierarchical":[40,109,133],"Dual":[41],"Transformer":[42,111,135],"(HDTR)":[43],"to":[44,94,101,112,117,136,145],"explore":[45],"contribution":[47],"typical":[50],"structural":[51,158],"priors":[52],"object":[55,70,161,193],"parts.":[56],"HDTR":[57,88],"first":[58],"generates":[59,89],"pyramid":[61],"multi-granularity":[62,126],"pixel":[63,92,127,148],"representations":[64],"under":[65],"supervision":[67],"maps":[73],"at":[74],"different":[75],"levels":[77],"and":[78,166,180],"then":[79],"assigns":[80],"each":[81],"region":[82],"an":[83,90],"initial":[84],"embedding.":[86],"Moreover,":[87],"edge":[91],"representation":[93],"extend":[95],"capability":[97],"network":[100],"capture":[102],"detailed":[103],"information.":[104],"Afterward,":[105],"design":[107],"a":[108,132,188],"Part":[110],"upgrade":[113],"embeddings":[116,144],"their":[118],"counterparts":[120],"with":[121],"assistance":[123],"representations.":[128,149],"Next,":[129],"Pixel":[134],"infer":[137],"information":[140],"from":[141],"enrich":[146],"Note":[150],"that":[151,184],"both":[152],"transformer":[153],"decoders":[154],"rely":[155],"on":[156,171],"relations":[159],"between":[160],"i.e.,":[163,175],"dependency,":[164],"composition,":[165],"decomposition":[167],"relations.":[168],"experiments":[170],"five":[172],"large-scale":[173],"datasets,":[174],"LaPa,":[176],"CelebAMask-HQ,":[177],"CIHP,":[178],"LIP":[179],"Pascal":[181],"Animal,":[182],"demonstrate":[183],"our":[185],"method":[186],"sets":[187],"new":[189],"state-of-the-art":[190],"performance":[191],"for":[192],"parsing.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}