{"id":"https://openalex.org/W4372341147","doi":"https://doi.org/10.1109/icassp49357.2023.10095603","title":"Learning Task-Aligned Mask Query for Instance Segmentation","display_name":"Learning Task-Aligned Mask Query for Instance Segmentation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341147","doi":"https://doi.org/10.1109/icassp49357.2023.10095603"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095603","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095603","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":"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/A5101784533","display_name":"Bin Fu","orcid":"https://orcid.org/0000-0002-1526-8654"},"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":true,"raw_author_name":"Bin Fu","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,Shenzhen,China","School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807708","display_name":"Hongliang He","orcid":"https://orcid.org/0009-0004-7575-2570"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"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":"Hongliang He","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,Shenzhen,China","School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041227759","display_name":"Pengxu Wei","orcid":"https://orcid.org/0000-0002-2190-0767"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxu Wei","raw_affiliation_strings":["Sun Yat-sen University,Guangzhou,China","Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332984","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0002-9765-4523"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"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":"Jie Chen","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,Shenzhen,China","Peng Cheng Laboratory, Shenzhen, China","School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101784533"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03718039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9962000250816345,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9952999949455261,"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":0.8359894752502441},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7340764999389648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6448657512664795},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5640447735786438},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5087934136390686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48070937395095825},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4631959795951843},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.46207597851753235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4404102563858032},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.41476064920425415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3659874200820923},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.2873257100582123},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1685684621334076},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1460338532924652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359894752502441},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7340764999389648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448657512664795},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5640447735786438},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5087934136390686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48070937395095825},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4631959795951843},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46207597851753235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4404102563858032},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.41476064920425415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659874200820923},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2873257100582123},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1685684621334076},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1460338532924652},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095603","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095603","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2920326761","https://openalex.org/W2963849369","https://openalex.org/W3035358681","https://openalex.org/W3047032303","https://openalex.org/W3092462694","https://openalex.org/W3093600664","https://openalex.org/W3102710196","https://openalex.org/W3106546328","https://openalex.org/W3138516171","https://openalex.org/W3168783492","https://openalex.org/W3176659256","https://openalex.org/W3177248696","https://openalex.org/W3177269789","https://openalex.org/W3213165621","https://openalex.org/W4214507171","https://openalex.org/W4214613769","https://openalex.org/W4312312588","https://openalex.org/W4312815172","https://openalex.org/W6639102338","https://openalex.org/W6735463952","https://openalex.org/W6775515071","https://openalex.org/W6779586474","https://openalex.org/W6781358803","https://openalex.org/W6784094891","https://openalex.org/W6784930956","https://openalex.org/W6796402304","https://openalex.org/W6797347943","https://openalex.org/W6797784111","https://openalex.org/W6798837711"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W1546381263"],"abstract_inverted_index":{"Recently,":[0],"query-based":[1],"instance":[2,58,70],"segmentation":[3,25,59,91],"methods":[4],"have":[5],"achieved":[6],"comparable":[7],"performance":[8,130],"to":[9,30,79,104],"previous":[10],"state-of-the-art":[11,132],"methods.":[12],"However,":[13],"the":[14,17,20,95,107,117],"query":[15],"lacks":[16],"learning":[18],"of":[19,94,116],"consistency":[21],"between":[22,32],"classification":[23,33,111],"and":[24,35,41,86,113],"tasks,":[26],"which":[27,63,89],"may":[28],"lead":[29],"misalignment":[31],"score":[34,112],"mask":[36,39,67,96,114],"quality":[37,92,115],"(i.e.,":[38],"IoU)":[40],"can":[42],"not":[43],"result":[44],"in":[45],"a":[46,56],"reliable":[47],"ranking":[48],"for":[49,69,83,110],"predictions.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,73],"propose":[55,74],"novel":[57],"method,":[60],"termed":[61],"AlignMask,":[62],"effectively":[64],"learns":[65],"task-aligned":[66,81],"queries":[68],"end-toend.":[71],"Specifically,":[72],"Aligned":[75,101],"Query":[76],"Learning":[77],"(AQL)":[78],"learn":[80],"features":[82],"pixel":[84],"embedding":[85],"transformer":[87],"decoder,":[88],"helps":[90],"estimation":[93],"query.":[97,118],"We":[98],"also":[99],"use":[100],"Label":[102],"Assignment":[103],"explicitly":[105],"align":[106],"optimization":[108],"goals":[109],"Extensive":[119],"experiments":[120],"on":[121],"MSCOCO":[122],"show":[123],"that":[124],"our":[125],"proposed":[126],"AlignMask":[127],"achieves":[128],"competitive":[129],"with":[131],"models.":[133]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}