{"id":"https://openalex.org/W4386918829","doi":"https://doi.org/10.1109/tmm.2023.3318075","title":"GIN: Generative INvariant Shape Prior for Amodal Instance Segmentation","display_name":"GIN: Generative INvariant Shape Prior for Amodal Instance Segmentation","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4386918829","doi":"https://doi.org/10.1109/tmm.2023.3318075"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3318075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3318075","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":"Zhixuan Li","orcid":"https://orcid.org/0000-0002-2558-508X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixuan Li","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2558-508X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044723571","display_name":"Weining Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weining Ye","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9352-0448","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101606698","display_name":"Tingting Jiang","orcid":"https://orcid.org/0000-0002-5372-0656"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Jiang","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5372-0656","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058066577","display_name":"Tiejun Huang","orcid":"https://orcid.org/0000-0002-4234-6099"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Huang","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","Beijing Academy of Artificial Intelligence, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4234-6099","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7018,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8682181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"3924","last_page":"3936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983000159263611,"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":0.9983000159263611,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9943000078201294,"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":0.9905999898910522,"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/amodal-perception","display_name":"Amodal perception","score":0.816723108291626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783459424972534},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6422256231307983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316480040550232},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6133679151535034},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.568488359451294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5013751983642578},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4857907295227051},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4519651532173157},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4283282160758972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1345078945159912},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.07217743992805481}],"concepts":[{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.816723108291626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783459424972534},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6422256231307983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316480040550232},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6133679151535034},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.568488359451294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5013751983642578},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4857907295227051},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4519651532173157},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4283282160758972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1345078945159912},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.07217743992805481},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3318075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3318075","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1646986031","https://openalex.org/W1784617778","https://openalex.org/W1861492603","https://openalex.org/W2018462007","https://openalex.org/W2019306035","https://openalex.org/W2069570550","https://openalex.org/W2134383016","https://openalex.org/W2150066425","https://openalex.org/W2174282328","https://openalex.org/W2194775991","https://openalex.org/W2344939607","https://openalex.org/W2482581235","https://openalex.org/W2604176797","https://openalex.org/W2792937288","https://openalex.org/W2798542761","https://openalex.org/W2883363148","https://openalex.org/W2897541487","https://openalex.org/W2920326761","https://openalex.org/W2945421731","https://openalex.org/W2947482671","https://openalex.org/W2963150697","https://openalex.org/W2963243172","https://openalex.org/W2963539956","https://openalex.org/W2963660453","https://openalex.org/W2963769056","https://openalex.org/W2963971305","https://openalex.org/W2964211168","https://openalex.org/W2964325922","https://openalex.org/W2968561718","https://openalex.org/W2982770724","https://openalex.org/W2990578105","https://openalex.org/W2993182889","https://openalex.org/W3034826836","https://openalex.org/W3035049382","https://openalex.org/W3035323039","https://openalex.org/W3035637413","https://openalex.org/W3084252700","https://openalex.org/W3088227529","https://openalex.org/W3095638603","https://openalex.org/W3096609285","https://openalex.org/W3105765741","https://openalex.org/W3106546328","https://openalex.org/W3108815824","https://openalex.org/W3127947687","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3146455718","https://openalex.org/W3167260844","https://openalex.org/W3171516518","https://openalex.org/W3173230514","https://openalex.org/W4237938455","https://openalex.org/W4288325606","https://openalex.org/W4311967393","https://openalex.org/W4312394134","https://openalex.org/W4312498343","https://openalex.org/W4319778743","https://openalex.org/W4372267075","https://openalex.org/W4390874836","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6749224410","https://openalex.org/W6750697433","https://openalex.org/W6754551998","https://openalex.org/W6764322716","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6785897658","https://openalex.org/W6793267612","https://openalex.org/W6845379652"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Amodal":[0],"instance":[1],"segmentation":[2,66],"(AIS)":[3],"predicts":[4],"the":[5,9,23,61,65,73,81,100,106,128,146],"complete":[6],"shape":[7,47,57,74,82,131],"of":[8,130],"occluded":[10,16,24],"object,":[11],"including":[12,114],"both":[13],"visible":[14],"and":[15,59,117,140,160],"regions.":[17],"Because":[18],"visual":[19],"clues":[20],"are":[21],"lacking,":[22],"region":[25],"is":[26,37,77,110,137],"difficult":[27],"to":[28,64,87,112],"segment":[29],"accurately.":[30],"In":[31,84],"human":[32,101],"amodal":[33],"perception,":[34],"shape-prior":[35,96],"knowledge":[36],"helpful":[38],"for":[39],"AIS.":[40],"The":[41],"previous":[42],"method":[43],"uses":[44],"a":[45,56,93],"2D":[46],"prior":[48],"by":[49],"<italic":[50,121],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[51,122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">rote":[52],"memorizing</i>":[53],",":[54],"establishing":[55],"dictionary":[58,143],"retrieving":[60],"closest":[62],"mask":[63],"result.":[67],"However,":[68],"this":[69,85],"approach":[70],"cannot":[71],"obtain":[72],"prior,":[75],"which":[76,109],"not":[78],"prestored":[79],"in":[80],"dictionary.":[83],"article,":[86],"improve":[88],"generalization":[89],"ability,":[90],"we":[91],"propose":[92],"generative":[94],"invariant":[95,111],"network":[97],"(GIN),":[98],"simulating":[99],"perception":[102],"process":[103],"that":[104,126],"learns":[105],"basic":[107],"shape,":[108],"transformations,":[113],"translation,":[115],"rotation,":[116],"scaling.":[118],"We":[119],"design":[120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">a":[123],"novel":[124],"framework":[125],"decouples":[127],"learning":[129],"priors":[132],"from":[133],"transformation</i>":[134],".":[135],"GIN":[136,150],"end-to-end":[138],"trainable":[139],"needs":[141],"no":[142],"establishment,":[144],"making":[145],"whole":[147],"pipeline":[148],"efficient.":[149],"outperforms":[151],"state-of-the-art":[152],"methods":[153],"on":[154],"three":[155],"public":[156],"datasets":[157],"(D2SA,":[158],"COCOA-cls,":[159],"KINS)":[161],"with":[162],"large":[163],"margins.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}