{"id":"https://openalex.org/W4224923656","doi":"https://doi.org/10.1109/icassp43922.2022.9746367","title":"SDETR: Attention-Guided Salient Object Detection with Transformer","display_name":"SDETR: Attention-Guided Salient Object Detection with Transformer","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224923656","doi":"https://doi.org/10.1109/icassp43922.2022.9746367"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746367","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/A5036976698","display_name":"Guanze Liu","orcid":"https://orcid.org/0009-0002-3475-1745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanze Liu","raw_affiliation_strings":["OPPO Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635207","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-6379-7617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["OPPO Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101554844","display_name":"Han Huang","orcid":"https://orcid.org/0000-0002-1760-5757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Huang","raw_affiliation_strings":["OPPO Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104107223","display_name":"Cheng Lu","orcid":"https://orcid.org/0009-0006-5324-5361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Lu","raw_affiliation_strings":["Xmotors"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xmotors","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038064028","display_name":"Yandong Guo","orcid":"https://orcid.org/0000-0002-4594-8415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yandong Guo","raw_affiliation_strings":["OPPO Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2359,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55710939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1611","last_page":"1615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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/T11094","display_name":"Face Recognition and Perception","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9700000286102295,"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":0.7851263284683228},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6863958835601807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6008428931236267},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5930086374282837},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5859623551368713},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5671353936195374},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5447574257850647},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5326853394508362},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.521065890789032},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5045479536056519},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4712546169757843},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46157559752464294},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41721469163894653},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36015206575393677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851263284683228},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6863958835601807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6008428931236267},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5930086374282837},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5859623551368713},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5671353936195374},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5447574257850647},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5326853394508362},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.521065890789032},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5045479536056519},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4712546169757843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46157559752464294},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41721469163894653},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36015206575393677},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746367","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1894057436","https://openalex.org/W2002781701","https://openalex.org/W2039313011","https://openalex.org/W2086791339","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2740667773","https://openalex.org/W2939217524","https://openalex.org/W2961348656","https://openalex.org/W2963112696","https://openalex.org/W2987701848","https://openalex.org/W2990984982","https://openalex.org/W2998449272","https://openalex.org/W3025800305","https://openalex.org/W3035290198","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3153906112","https://openalex.org/W3165150763","https://openalex.org/W3170841864","https://openalex.org/W3211490618","https://openalex.org/W6639102338","https://openalex.org/W6639359414","https://openalex.org/W6793746569","https://openalex.org/W6795592662","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4298525700","https://openalex.org/W2953362004","https://openalex.org/W2549121492"],"abstract_inverted_index":{"Most":[0],"existing":[1],"CNN-based":[2],"salient":[3,21],"object":[4,22],"detection":[5],"methods":[6],"can":[7,72,124],"identify":[8],"fine-grained":[9,80],"segmentation":[10],"details":[11],"like":[12],"hair":[13],"and":[14,68,79,120],"animal":[15],"fur,":[16],"but":[17],"often":[18],"mispredict":[19],"the":[20,40,49,95,111,127],"due":[23],"to":[24,47,62,93],"lack":[25],"of":[26,39,66],"global":[27],"contextual":[28],"information":[29],"caused":[30,98],"by":[31,99],"locality":[32],"convolution":[33],"layers.":[34],"The":[35],"limited":[36],"training":[37,101],"data":[38],"current":[41],"SOD":[42,92,123],"task":[43],"adds":[44],"additional":[45],"difficulty":[46],"capture":[48],"saliency":[50,77],"information.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56,85],"a":[57,86],"two-stage":[58],"predict-refine":[59],"SDETR":[60,112],"model":[61,128],"leverage":[63],"both":[64],"benefits":[65],"transformer":[67],"CNN":[69],"layers":[70],"that":[71,110],"produce":[73],"results":[74],"with":[75],"accurate":[76],"prediction":[78],"local":[81],"details.":[82],"We":[83],"also":[84],"novel":[87],"pre-train":[88],"dataset":[89],"annotation":[90],"COCO":[91,122],"erase":[94],"overfitting":[96],"problem":[97],"insufficient":[100],"data.":[102],"Comprehensive":[103],"experiments":[104],"on":[105,116,130],"five":[106],"benchmark":[107],"datasets":[108],"demonstrate":[109],"outperforms":[113],"state-of-the-art":[114],"approaches":[115],"four":[117],"evaluation":[118],"metrics,":[119],"our":[121],"largely":[125],"improve":[126],"performance":[129],"DUTS,":[131],"ECSSD,":[132],"DUT,":[133],"PASCAL-S":[134],"datasets.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}