{"id":"https://openalex.org/W4391305973","doi":"https://doi.org/10.1109/smc53992.2023.10394249","title":"Semantic Segmentation Based on Vision Transformer via Interactive Attention","display_name":"Semantic Segmentation Based on Vision Transformer via Interactive Attention","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391305973","doi":"https://doi.org/10.1109/smc53992.2023.10394249"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394249","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5045753906","display_name":"Tao Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qiu","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066408400","display_name":"Yu Xiao","orcid":"https://orcid.org/0000-0002-0911-6857"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xiao","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703892","display_name":"Qi Yang","orcid":"https://orcid.org/0000-0001-6969-8724"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074958556","display_name":"Xinqi Jiang","orcid":"https://orcid.org/0009-0002-7503-0231"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinqi Jiang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101664915","display_name":"Taiping Zhang","orcid":"https://orcid.org/0000-0001-9891-4203"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiping Zhang","raw_affiliation_strings":["College of Computer Science, Chongqing University,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"413","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.850507915019989},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.698636531829834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6871082186698914},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6048731207847595},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.592621922492981},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5088677406311035},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.48118478059768677},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4786280691623688},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4643894135951996},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43351417779922485},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.430692583322525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37323153018951416},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07036581635475159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850507915019989},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.698636531829834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6871082186698914},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6048731207847595},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.592621922492981},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5088677406311035},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.48118478059768677},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4786280691623688},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4643894135951996},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43351417779922485},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.430692583322525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37323153018951416},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07036581635475159},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394249","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5656631925","display_name":null,"funder_award_id":"62076043","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W1923697677","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2560023338","https://openalex.org/W2601564443","https://openalex.org/W2612690371","https://openalex.org/W2737258237","https://openalex.org/W2752782242","https://openalex.org/W2787091153","https://openalex.org/W2884585870","https://openalex.org/W2955058313","https://openalex.org/W2963091558","https://openalex.org/W2963136578","https://openalex.org/W2963727650","https://openalex.org/W2963881378","https://openalex.org/W2981689412","https://openalex.org/W2982220924","https://openalex.org/W2991471181","https://openalex.org/W3035071066","https://openalex.org/W3097065222","https://openalex.org/W3133630855","https://openalex.org/W3138516171","https://openalex.org/W3157528469","https://openalex.org/W3159637683","https://openalex.org/W3170841864","https://openalex.org/W3211490618","https://openalex.org/W4214893857","https://openalex.org/W4246193833"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,30],"is":[2],"a":[3,80],"fundamental":[4],"task":[5],"in":[6,40,49,141],"the":[7,25,33,37,50,66,73,86,111,138],"computer":[8],"vision":[9],"community":[10],"that":[11,137],"aims":[12],"to":[13,46,72,97,118],"achieve":[14],"pixel-wise":[15],"classification":[16],"of":[17,27,36,52,124],"images.":[18],"Convolutional":[19],"Neural":[20],"Networks":[21],"(CNNs)":[22],"have":[23],"been":[24],"backbone":[26],"typical":[28],"semantic":[29,54],"methods.":[31],"However,":[32],"recent":[34],"success":[35],"Transformer":[38],"architecture":[39],"natural":[41],"language":[42],"processing":[43],"has":[44],"led":[45],"its":[47],"application":[48],"field":[51],"image":[53],"segmentation.":[55],"These":[56],"methods":[57],"mainly":[58],"focus":[59],"on":[60,130],"learning":[61],"more":[62],"effective":[63],"information":[64,102],"through":[65],"encoder,":[67],"while":[68],"paying":[69],"less":[70],"attention":[71,96],"decoder.":[74],"In":[75,88],"this":[76,142],"paper,":[77],"we":[78,109],"propose":[79,110],"novel":[81],"attention-based":[82],"decoder":[83],"module":[84,93],"called":[85],"Attention":[87,89],"(AIA)":[90],"module.":[91],"This":[92],"employs":[94],"interactive":[95],"extract":[98],"spatial":[99],"and":[100,103,134],"channel":[101],"dynamically":[104],"determine":[105],"feature":[106,120],"importance.":[107],"Additionally,":[108],"Feature":[112],"Position":[113],"Offset":[114],"Estimation":[115],"Module":[116],"(FPOEM)":[117],"mitigate":[119],"misalignment":[121],"when":[122],"features":[123],"different":[125],"scales":[126],"are":[127],"fused.":[128],"Experiments":[129],"two":[131],"datasets,":[132],"Cityscapes":[133],"ADE20K,":[135],"show":[136],"method":[139],"proposed":[140],"paper":[143],"achieves":[144],"state-of-the-art":[145],"performance.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}