{"id":"https://openalex.org/W4402353440","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650837","title":"ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation","display_name":"ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353440","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650837"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5053495766","display_name":"Minh\u2013Triet Tran","orcid":"https://orcid.org/0000-0003-3046-3041"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minh Tran","raw_affiliation_strings":["University of Arkansas,AICV Lab,Department of EECS,USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,AICV Lab,Department of EECS,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094196477","display_name":"Winston Bounsavy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Winston Bounsavy","raw_affiliation_strings":["University of Arkansas,AICV Lab,Department of EECS,USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,AICV Lab,Department of EECS,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052144407","display_name":"Viet-Khoa Vo-Ho","orcid":"https://orcid.org/0000-0003-0277-7094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khoa Vo","raw_affiliation_strings":["University of Arkansas,AICV Lab,Department of EECS,USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,AICV Lab,Department of EECS,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089006585","display_name":"Anh Nguyen","orcid":"https://orcid.org/0000-0002-1449-211X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anh Nguyen","raw_affiliation_strings":["University of Liverpool,Department of CS,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of CS,UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072417690","display_name":"Tri Nguyen","orcid":"https://orcid.org/0000-0003-0670-0414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tri Nguyen","raw_affiliation_strings":["Cruise LLC,USA"],"affiliations":[{"raw_affiliation_string":"Cruise LLC,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023725893","display_name":"Ngan Le","orcid":"https://orcid.org/0000-0003-2571-0511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngan Le","raw_affiliation_strings":["University of Arkansas,AICV Lab,Department of EECS,USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,AICV Lab,Department of EECS,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053495766"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7509,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91692251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9983999729156494,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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":0.9929999709129333,"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":0.9730013608932495},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.656871497631073},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.625961184501648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6083327531814575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4850546717643738},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35056987404823303},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1025020182132721},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09390577673912048},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08521273732185364},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.07882243394851685},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06380864977836609}],"concepts":[{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.9730013608932495},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.656871497631073},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.625961184501648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083327531814575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4850546717643738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35056987404823303},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1025020182132721},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09390577673912048},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08521273732185364},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.07882243394851685},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06380864977836609},{"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:10.1109/ijcnn60899.2024.10650837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2050830699","https://openalex.org/W2194775991","https://openalex.org/W2344939607","https://openalex.org/W2523246573","https://openalex.org/W2963150697","https://openalex.org/W2963243172","https://openalex.org/W2963270286","https://openalex.org/W2963660453","https://openalex.org/W2964325922","https://openalex.org/W2982770724","https://openalex.org/W3035637413","https://openalex.org/W3107761599","https://openalex.org/W3167260844","https://openalex.org/W3173230514","https://openalex.org/W3200139538","https://openalex.org/W3201721053","https://openalex.org/W4256003687","https://openalex.org/W4306178259","https://openalex.org/W4307312817","https://openalex.org/W4312280796","https://openalex.org/W4312940821","https://openalex.org/W4385245566","https://openalex.org/W6846328747"],"related_works":["https://openalex.org/W2951289157","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Amodal":[0,138],"Instance":[1],"Segmentation":[2],"(AIS)":[3],"presents":[4],"a":[5,26,97,102],"challenging":[6],"task":[7],"as":[8],"it":[9],"involves":[10],"predicting":[11,130,142],"both":[12,30],"visible":[13,37,42,63,76,83,131],"and":[14,40,113,144,147,161],"occluded":[15,145],"parts":[16],"of":[17,54,70,82,172],"objects":[18],"within":[19],"images.":[20],"Existing":[21],"AIS":[22,167],"methods":[23],"rely":[24],"on":[25],"bidirectional":[27],"approach,":[28],"encompassing":[29],"the":[31,52,58,62,67,86,107,115,170],"transition":[32],"from":[33,41],"amodal":[34,45,55,143],"features":[35,38,43,46,56,64,84],"to":[36,44,66,154],"(amodal-to-visible)":[39],"(visible-to-amodal).":[47],"Our":[48],"observation":[49],"shows":[50],"that":[51],"utilization":[53],"through":[57],"amodal-to-visible":[59,118],"can":[60],"confuse":[61],"due":[65],"extra":[68],"information":[69],"occluded/hidden":[71],"segments":[72],"not":[73],"presented":[74],"in":[75],"display.":[77],"Consequently,":[78],"this":[79,92],"compromised":[80],"quality":[81],"during":[85],"subsequent":[87],"visible-to-amodal":[88,103],"transition.":[89,104],"To":[90],"tackle":[91],"issue,":[93],"we":[94],"introduce":[95],"ShapeFormer,":[96],"decoupled":[98],"Transformer-based":[99],"model":[100],"with":[101,133],"It":[105],"facilitates":[106],"explicit":[108],"relationship":[109],"between":[110],"output":[111],"segmentations":[112],"avoids":[114],"need":[116],"for":[117,129,141],"transitions.":[119],"ShapeFormer":[120],"comprises":[121],"three":[122],"key":[123],"modules:":[124],"(i)":[125],"Visible-Occluding":[126],"Mask":[127,139],"Head":[128,140],"segmentation":[132],"occlusion":[134],"awareness,":[135],"(ii)":[136],"Shape-Prior":[137],"masks,":[146],"(iii)":[148],"Category-Specific":[149],"Shape":[150],"Prior":[151],"Retriever":[152],"aims":[153],"provide":[155],"shape":[156],"prior":[157],"knowledge.":[158],"Comprehensive":[159],"experiments":[160],"extensive":[162],"ablation":[163],"studies":[164],"across":[165],"various":[166],"benchmarks":[168],"demonstrate":[169],"effectiveness":[171],"our":[173],"ShapeFormer.":[174],"The":[175],"code":[176],"is":[177],"available":[178],"at:":[179],"https:":[180],"//github.com/UARK-AICV/ShapeFormer":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}