{"id":"https://openalex.org/W4403791281","doi":"https://doi.org/10.1145/3664647.3680650","title":"Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection","display_name":"Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791281","doi":"https://doi.org/10.1145/3664647.3680650"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680650","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5109519668","display_name":"S. Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixuan Gao","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0006-4251-2495","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451855","display_name":"Pingping Zhang","orcid":"https://orcid.org/0000-0003-1206-1444"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingping Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1206-1444","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyu Yan","orcid":"https://orcid.org/0009-0003-2249-3985"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Yan","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0003-2249-3985","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9894","last_page":"9903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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/T11605","display_name":"Visual Attention and Saliency Detection","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/T11094","display_name":"Face Recognition and Perception","score":0.9376000165939331,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9304999709129333,"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":0.7497718334197998},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.686058759689331},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6335650086402893},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5576686263084412},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5059911608695984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47822803258895874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44847628474235535},{"id":"https://openalex.org/keywords/object-based","display_name":"Object based","score":0.4152637720108032},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32011979818344116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26927250623703003},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07645180821418762},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07570311427116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497718334197998},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.686058759689331},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6335650086402893},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5576686263084412},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5059911608695984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47822803258895874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44847628474235535},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.4152637720108032},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32011979818344116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26927250623703003},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07645180821418762},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07570311427116394}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680650","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1954128991","https://openalex.org/W1982075130","https://openalex.org/W2002781701","https://openalex.org/W2039313011","https://openalex.org/W2086791339","https://openalex.org/W2194775991","https://openalex.org/W2612690371","https://openalex.org/W2740667773","https://openalex.org/W2780708736","https://openalex.org/W2903642350","https://openalex.org/W2908622466","https://openalex.org/W2963032190","https://openalex.org/W2963112696","https://openalex.org/W2963868681","https://openalex.org/W2963906836","https://openalex.org/W2972332787","https://openalex.org/W2989161706","https://openalex.org/W2990201021","https://openalex.org/W2990278031","https://openalex.org/W2998449272","https://openalex.org/W3034185160","https://openalex.org/W3035422681","https://openalex.org/W3080223684","https://openalex.org/W3107944836","https://openalex.org/W3121523901","https://openalex.org/W3122006940","https://openalex.org/W3138516171","https://openalex.org/W4212774754","https://openalex.org/W4214506192","https://openalex.org/W4214561053","https://openalex.org/W4234552385","https://openalex.org/W4283806547","https://openalex.org/W4313546627","https://openalex.org/W4386072314","https://openalex.org/W4387968376","https://openalex.org/W4390190100","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4391992698","https://openalex.org/W4400409506","https://openalex.org/W4402660119","https://openalex.org/W6788627440"],"related_works":["https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W2100786069","https://openalex.org/W3205182086","https://openalex.org/W4239112351","https://openalex.org/W4256166021","https://openalex.org/W2585146553","https://openalex.org/W2156352682","https://openalex.org/W4298625047","https://openalex.org/W1991139010"],"abstract_inverted_index":{"Salient":[0],"Object":[1],"Detection":[2],"(SOD)":[3],"aims":[4],"to":[5,121,138,156],"identify":[6],"and":[7,38,61,84,103,175],"segment":[8],"the":[9,80,90,141,145,165],"most":[10],"prominent":[11],"objects":[12],"in":[13,41,75],"images.":[14],"Advanced":[15],"SOD":[16,173],"methods":[17,33],"often":[18],"utilize":[19,140],"various":[20],"Convolutional":[21],"Neural":[22],"Networks":[23],"(CNN)":[24],"or":[25],"Transformers":[26],"for":[27,107],"deep":[28],"feature":[29],"extraction.":[30],"However,":[31],"these":[32,97],"still":[34],"deliver":[35],"low":[36],"performance":[37,167],"poor":[39],"generalization":[40,62,178],"complex":[42],"cases.":[43],"Recently,":[44],"Segment":[45],"Anything":[46],"Model":[47],"(SAM)":[48],"has":[49],"been":[50],"proposed":[51],"as":[52,87,89],"a":[53,101,113,133,151],"visual":[54],"fundamental":[55],"model,":[56],"which":[57,72,118],"gives":[58],"strong":[59,177],"segmentation":[60,181],"capabilities.":[63],"Nonetheless,":[64],"SAM":[65,78,105,120,158],"requires":[66],"accurate":[67],"prompts":[68],"of":[69,82,92,168],"target":[70],"objects,":[71],"are":[73],"unavailable":[74],"SOD.":[76,108],"Additionally,":[77],"lacks":[79],"utilization":[81],"multi-scale":[83,123],"multi-level":[85,142],"information,":[86],"well":[88],"incorporation":[91],"fine-grained":[93,160],"details.":[94,161],"To":[95],"address":[96],"shortcomings,":[98],"we":[99,110,131,149],"propose":[100,132,150],"Multi-scale":[102],"Detail-enhanced":[104],"(MDSAM)":[106],"Specifically,":[109],"first":[111],"introduce":[112],"Lightweight":[114],"Multi-Scale":[115],"Adapter":[116],"(LMSA),":[117],"allows":[119],"learn":[122],"information":[124,143],"with":[125,159],"very":[126],"few":[127],"trainable":[128],"parameters.":[129],"Then,":[130],"Multi-Level":[134],"Fusion":[135],"Module":[136,154],"(MLFM)":[137],"comprehensively":[139],"from":[144],"SAM's":[146],"encoder.":[147],"Finally,":[148],"Detail":[152],"Enhancement":[153],"(DEM)":[155],"incorporate":[157],"Experimental":[162],"results":[163],"demonstrate":[164],"superior":[166],"our":[169],"model":[170],"on":[171,179],"multiple":[172],"datasets":[174],"its":[176],"other":[180],"tasks.":[182],"The":[183],"source":[184],"code":[185],"is":[186],"released":[187],"at":[188],"https://github.com/BellyBeauty/MDSAM":[189]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}