{"id":"https://openalex.org/W4372267075","doi":"https://doi.org/10.1109/icassp49357.2023.10096534","title":"OAFormer: Learning Occlusion Distinguishable Feature for Amodal Instance Segmentation","display_name":"OAFormer: Learning Occlusion Distinguishable Feature for Amodal Instance Segmentation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267075","doi":"https://doi.org/10.1109/icassp49357.2023.10096534"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101540014","display_name":"Zhixuan Li","orcid":"https://orcid.org/0009-0003-7215-3209"},"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":["Peking University,Advanced Institute of Information Technology,Hangzhou,China","Advanced Institute of Information Technology, Peking University, Hangzhou, China","National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Advanced Institute of Information Technology,Hangzhou,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Advanced Institute of Information Technology, Peking University, Hangzhou, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018473196","display_name":"Ruohua Shi","orcid":"https://orcid.org/0000-0003-2895-1716"},"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":"Ruohua Shi","raw_affiliation_strings":["Peking University,National Engineering Research Center of Visual Technology, School of Computer Science,Beijing,China","National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,National Engineering Research Center of Visual Technology, School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Huang","raw_affiliation_strings":["Peking University,National Engineering Research Center of Visual Technology, School of Computer Science,Beijing,China","National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,National Engineering Research Center of Visual Technology, School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","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":["Peking University,Advanced Institute of Information Technology,Hangzhou,China","National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","Advanced Institute of Information Technology, Peking University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Advanced Institute of Information Technology,Hangzhou,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Advanced Institute of Information Technology, Peking University, Hangzhou, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"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":0.9979000091552734,"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":0.9979000091552734,"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":0.9939000010490417,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9926999807357788,"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":0.9064322710037231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7931442260742188},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7390308380126953},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7242273092269897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133748531341553},{"id":"https://openalex.org/keywords/occlusion","display_name":"Occlusion","score":0.6944819688796997},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5223559141159058},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.506794273853302},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4635637700557709},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44290050864219666},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.13375908136367798},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09296190738677979}],"concepts":[{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.9064322710037231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7931442260742188},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7390308380126953},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7242273092269897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133748531341553},{"id":"https://openalex.org/C2776268601","wikidata":"https://www.wikidata.org/wiki/Q968808","display_name":"Occlusion","level":2,"score":0.6944819688796997},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5223559141159058},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.506794273853302},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4635637700557709},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44290050864219666},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.13375908136367798},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09296190738677979},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C164705383","wikidata":"https://www.wikidata.org/wiki/Q10379","display_name":"Cardiology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2344939607","https://openalex.org/W2482581235","https://openalex.org/W2604176797","https://openalex.org/W2734349601","https://openalex.org/W2947482671","https://openalex.org/W2948467257","https://openalex.org/W2963150697","https://openalex.org/W2963243172","https://openalex.org/W2963660453","https://openalex.org/W2964325922","https://openalex.org/W2990578105","https://openalex.org/W3035637413","https://openalex.org/W3095638603","https://openalex.org/W3105765741","https://openalex.org/W3108815824","https://openalex.org/W3128211327","https://openalex.org/W3167260844","https://openalex.org/W3173230514","https://openalex.org/W3200139538","https://openalex.org/W4312498343","https://openalex.org/W4312815172","https://openalex.org/W6632211587","https://openalex.org/W6721671007"],"related_works":["https://openalex.org/W3158435931","https://openalex.org/W1589158839","https://openalex.org/W2048200892","https://openalex.org/W4284674805","https://openalex.org/W4387775854","https://openalex.org/W4321460497","https://openalex.org/W2153903859","https://openalex.org/W4294017904","https://openalex.org/W2086050082","https://openalex.org/W2951289157"],"abstract_inverted_index":{"The":[0,105],"Amodal":[1],"Instance":[2],"Segmentation":[3],"(AIS)":[4],"task":[5],"aims":[6],"to":[7,30,59,76,110,120,123,136],"infer":[8],"the":[9,43,57,62,74,80,112,138],"complete":[10],"mask":[11],"of":[12,46,82,107,140],"occluded":[13,21],"instance.":[14,86],"Under":[15],"many":[16],"circumstances,":[17],"existing":[18,36],"methods":[19,38,58,146],"treat":[20],"objects":[22,64],"as":[23,49],"unoccluded":[24],"ones,":[25],"and":[26],"vice":[27],"versa,":[28],"leading":[29],"inaccurate":[31],"predictions.":[32],"This":[33],"is":[34,54,71,98,109],"because":[35],"AIS":[37,134],"do":[39],"not":[40],"explicitly":[41],"utilize":[42],"occlusion":[44,52,83,113,125],"rates":[45],"each":[47,85],"object":[48],"supervision.":[50],"However,":[51],"information":[53],"critical":[55],"for":[56,73,84,100],"recognize":[60],"whether":[61],"target":[63],"are":[65,118],"occluded.":[66],"Hence":[67],"we":[68],"believe":[69],"it":[70],"vital":[72],"method":[75],"be":[77,124],"distinguishable":[78],"about":[79],"degree":[81],"In":[87],"this":[88],"paper,":[89],"a":[90],"simple":[91],"yet":[92],"effective":[93],"Occlusion-aware":[94],"transformer-based":[95],"model,":[96],"OAFormer,":[97],"proposed":[99,119],"accurate":[101],"amodal":[102],"instance":[103],"segmentation.":[104],"goal":[106],"OAFormer":[108,122,143],"learn":[111],"discriminative":[114],"features.":[115],"Novel":[116],"components":[117],"enable":[121],"distinguishable.":[126],"We":[127],"conduct":[128],"extensive":[129],"experiments":[130],"on":[131],"two":[132],"challenging":[133],"datasets":[135],"evaluate":[137],"effectiveness":[139],"our":[141],"method.":[142],"outperforms":[144],"state-of-the-art":[145],"by":[147],"large":[148],"margins.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}