{"id":"https://openalex.org/W4225275515","doi":"https://doi.org/10.1109/icassp43922.2022.9747246","title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","display_name":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225275515","doi":"https://doi.org/10.1109/icassp43922.2022.9747246"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747246","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5090152810","display_name":"Kaining Ying","orcid":"https://orcid.org/0000-0003-2596-1847"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaining Ying","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science and Technology","College of Computer Science and Technology, Zhejiang University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science and Technology","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395198","display_name":"Zhenhua Wang","orcid":"https://orcid.org/0009-0009-2054-4308"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Wang","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science and Technology","College of Computer Science and Technology, Zhejiang University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science and Technology","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013768600","display_name":"Cong Bai","orcid":"https://orcid.org/0000-0002-6177-3862"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Bai","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science and Technology","College of Computer Science and Technology, Zhejiang University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science and Technology","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040443096","display_name":"Pengfei Zhou","orcid":"https://orcid.org/0000-0003-2181-3804"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Zhou","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science and Technology","College of Computer Science and Technology, Zhejiang University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science and Technology","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090152810"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.5316,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7427598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2619","last_page":"2623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9977999925613403,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8490148782730103},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7264381051063538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7060954570770264},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6728449463844299},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6008437871932983},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5799136757850647},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5624964237213135},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5572559833526611},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5434856414794922},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5320872664451599},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.513174831867218},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4573684334754944},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41681498289108276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25712406635284424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490148782730103},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7264381051063538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7060954570770264},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6728449463844299},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6008437871932983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5799136757850647},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5624964237213135},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5572559833526611},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5434856414794922},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5320872664451599},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.513174831867218},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4573684334754944},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41681498289108276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25712406635284424},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747246","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":42,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2222512263","https://openalex.org/W2509680863","https://openalex.org/W2555182955","https://openalex.org/W2744404335","https://openalex.org/W2908510526","https://openalex.org/W2920326761","https://openalex.org/W2952819818","https://openalex.org/W2962676885","https://openalex.org/W2963150697","https://openalex.org/W2963236837","https://openalex.org/W2963659353","https://openalex.org/W2963857746","https://openalex.org/W2981851019","https://openalex.org/W2982161360","https://openalex.org/W3013975023","https://openalex.org/W3034681942","https://openalex.org/W3035022492","https://openalex.org/W3093600664","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3106546328","https://openalex.org/W3113410735","https://openalex.org/W3122239467","https://openalex.org/W3170841864","https://openalex.org/W3171162369","https://openalex.org/W3171516518","https://openalex.org/W3172752666","https://openalex.org/W3175199633","https://openalex.org/W4229720961","https://openalex.org/W4288325606","https://openalex.org/W4385245566","https://openalex.org/W6730410022","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6764322716","https://openalex.org/W6772372853","https://openalex.org/W6775515071","https://openalex.org/W6778485988","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6784930956"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2737719445","https://openalex.org/W4324315429","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W2182785089","https://openalex.org/W4312178642","https://openalex.org/W2890372105","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Most":[0],"instance":[1,33],"segmentation":[2,34],"models":[3],"are":[4,50,68],"not":[5],"end-to-end":[6,32],"trainable":[7],"due":[8],"to":[9,80],"either":[10],"the":[11,40,81,85],"incorporation":[12],"of":[13,46,62],"proposal":[14],"estimation":[15],"(RPN)":[16],"as":[17,24],"a":[18,25,30,44,72],"pre-processing":[19],"or":[20],"non-maximum":[21],"suppression":[22],"(NMS)":[23],"post-processing.":[26],"Here":[27],"we":[28],"propose":[29],"novel":[31],"method":[35,87],"termed":[36],"ISDA.":[37],"It":[38],"reshapes":[39],"task":[41],"into":[42],"predicting":[43],"set":[45],"object":[47],"masks,":[48],"which":[49],"generated":[51],"via":[52],"traditional":[53],"convolution":[54],"operation":[55],"with":[56,76,108],"learned":[57,69],"position-aware":[58],"kernels":[59,65],"and":[60,66,103],"features":[61,67],"objects.":[63],"Such":[64],"by":[70,98],"leveraging":[71],"deformable":[73],"attention":[74],"network":[75],"multi-scale":[77],"representation.":[78],"Thanks":[79],"introduced":[82],"set-prediction":[83],"mechanism,":[84],"proposed":[86],"is":[88],"NMS-free.":[89],"Empirically,":[90],"ISDA":[91],"outperforms":[92],"Mask":[93],"R-CNN":[94],"(the":[95],"strong":[96],"baseline)":[97],"2.6":[99],"points":[100],"on":[101],"MS-COCO,":[102],"achieves":[104],"leading":[105],"performance":[106],"compared":[107],"recent":[109],"models.":[110],"Code":[111],"will":[112],"be":[113],"available":[114],"soon.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}