{"id":"https://openalex.org/W4387967934","doi":"https://doi.org/10.1145/3581783.3612212","title":"Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context","display_name":"Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967934","doi":"https://doi.org/10.1145/3581783.3612212"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612212","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5035069538","display_name":"Yicheng Song","orcid":"https://orcid.org/0009-0008-7104-8630"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Song","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-7104-8630","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048271189","display_name":"Shuyong Gao","orcid":"https://orcid.org/0000-0002-8992-0756"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyong Gao","raw_affiliation_strings":["Fudan University & Keenon Robotics Co., Ltd., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8992-0756","affiliations":[{"raw_affiliation_string":"Fudan University & Keenon Robotics Co., Ltd., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019021630","display_name":"Haozhe Xing","orcid":"https://orcid.org/0000-0001-5798-5152"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Xing","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5798-5152","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523911","display_name":"Yiting Cheng","orcid":"https://orcid.org/0000-0002-8331-9740"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiting Cheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8331-9740","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035140547","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-4953-2660"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4953-2660","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669255","display_name":"Wenqiang Zhang","orcid":"https://orcid.org/0000-0002-3339-8751"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3339-8751","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5532","last_page":"5541"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9775999784469604,"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":0.9692999720573425,"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/salient","display_name":"Salient","score":0.83770751953125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8234797120094299},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6885800957679749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6831949353218079},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5711577534675598},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5449116230010986},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5430448055267334},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4998667240142822},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48774582147598267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4716947376728058},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43569377064704895},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4304697513580322},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4278068542480469},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3984057605266571}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.83770751953125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234797120094299},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6885800957679749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6831949353218079},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5711577534675598},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5449116230010986},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5430448055267334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4998667240142822},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48774582147598267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4716947376728058},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43569377064704895},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4304697513580322},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4278068542480469},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3984057605266571},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612212","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7143284523","display_name":"\u52a8\u6001\u573a\u666f\u4e2d\u673a\u5668\u4eba\u663e\u8457\u6027\u76ee\u6807\u8bc6\u522b\u4e0e\u8868\u8fbe\u6280\u672f\u7814\u7a76","funder_award_id":"62072112","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1947031653","https://openalex.org/W1996326832","https://openalex.org/W2002781701","https://openalex.org/W2039313011","https://openalex.org/W2047670868","https://openalex.org/W2086791339","https://openalex.org/W2096733369","https://openalex.org/W2100470808","https://openalex.org/W2117539524","https://openalex.org/W2128340050","https://openalex.org/W2138621090","https://openalex.org/W2157364932","https://openalex.org/W2166650627","https://openalex.org/W2194775991","https://openalex.org/W2245000483","https://openalex.org/W2294182682","https://openalex.org/W2295107390","https://openalex.org/W2338972621","https://openalex.org/W2740667773","https://openalex.org/W2777511827","https://openalex.org/W2798991696","https://openalex.org/W2887361581","https://openalex.org/W2909051837","https://openalex.org/W2939217524","https://openalex.org/W2961348656","https://openalex.org/W2962852342","https://openalex.org/W2963112696","https://openalex.org/W2963136160","https://openalex.org/W2963198662","https://openalex.org/W2964352379","https://openalex.org/W2979579363","https://openalex.org/W3034140121","https://openalex.org/W3034453930","https://openalex.org/W3035290198","https://openalex.org/W3035422681","https://openalex.org/W3035524453","https://openalex.org/W3108318504","https://openalex.org/W3122412340","https://openalex.org/W3177087374","https://openalex.org/W3204446219","https://openalex.org/W4221142306","https://openalex.org/W4221167012","https://openalex.org/W4226080771","https://openalex.org/W4234552385","https://openalex.org/W4283806310","https://openalex.org/W4313025803","https://openalex.org/W4313153210","https://openalex.org/W4386066371"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Unsupervised":[0,160],"salient":[1,7,20,64,143],"object":[2,65],"detection":[3,66],"aims":[4],"to":[5,48,84,93,116,128,137,168],"detect":[6,138],"objects":[8,140],"without":[9],"using":[10],"supervision":[11],"signals":[12],"eliminating":[13],"the":[14,78,81,86,95,102,112,118,166,185,192],"tedious":[15],"task":[16],"of":[17,104,130,148,191],"manually":[18],"labeling":[19],"objects.":[21,171],"To":[22,151],"improve":[23],"training":[24],"efficiency,":[25],"end-to-end":[26,63,187],"methods":[27,188],"for":[28],"USOD":[29],"have":[30],"been":[31],"proposed":[32],"as":[33],"a":[34,61,158],"promising":[35],"alternative.":[36],"However,":[37],"current":[38,132],"solutions":[39],"rely":[40],"heavily":[41],"on":[42,174],"noisy":[43],"handcraft":[44],"labels":[45,120],"and":[46,189],"fail":[47],"mine":[49],"rich":[50],"semantic":[51],"information":[52,106],"from":[53,80],"deep":[54],"features.":[55],"In":[56],"this":[57,153],"paper,":[58],"we":[59,76,110,124,156],"propose":[60],"self-supervised":[62],"framework":[67],"via":[68],"top-down":[69],"context.":[70],"Specifically,":[71],"motivated":[72],"by":[73],"contrastive":[74],"learning,":[75],"exploit":[77,111],"self-localization":[79],"deepest":[82,108],"feature":[83],"construct":[85],"location":[87,119],"maps":[88],"which":[89],"are":[90,142],"then":[91],"leveraged":[92],"learn":[94],"most":[96,190],"instructive":[97],"segmentation":[98],"guidance.":[99],"Further":[100],"considering":[101],"lack":[103,129],"detailed":[105],"in":[107,144],"features,":[109],"detail-boosting":[113],"refiner":[114],"module":[115],"enrich":[117],"with":[121],"details.":[122],"Moreover,":[123],"observe":[125],"that":[126,141,178],"due":[127],"supervision,":[131],"unsupervised":[133],"saliency":[134],"models":[135],"tend":[136],"non-salient":[139,170],"some":[145],"other":[146],"samples":[147],"corresponding":[149],"scenarios.":[150],"address":[152],"widespread":[154],"issue,":[155],"design":[157],"novel":[159],"Non-Salient":[161],"Suppression":[162],"(UNSS)":[163],"method":[164,180],"developing":[165],"ability":[167],"ignore":[169],"Extensive":[172],"experiments":[173],"benchmark":[175],"datasets":[176],"demonstrate":[177],"our":[179],"achieves":[181],"leading":[182],"performance":[183],"among":[184],"recent":[186],"multi-stage":[193],"solutions.":[194],"The":[195],"code":[196],"is":[197],"available.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}