{"id":"https://openalex.org/W4403780636","doi":"https://doi.org/10.1145/3664647.3681119","title":"Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection","display_name":"Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780636","doi":"https://doi.org/10.1145/3664647.3681119"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681119","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/A5101262105","display_name":"Zhenni Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenni Yu","raw_affiliation_strings":["Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency, Wenzhou University, Wenzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-5435-481X","affiliations":[{"raw_affiliation_string":"Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency, Wenzhou University, Wenzhou, Zhejiang, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699785","display_name":"Xiaoqin Zhang","orcid":"https://orcid.org/0000-0003-0958-7285"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency, Wenzhou University, Wenzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-0958-7285","affiliations":[{"raw_affiliation_string":"Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency, Wenzhou University, Wenzhou, Zhejiang, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730692","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0001-5787-2705"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency, Wenzhou University, Wenzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5787-2705","affiliations":[{"raw_affiliation_string":"Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency, Wenzhou University, Wenzhou, Zhejiang, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["School of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9714-8738","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050524397","display_name":"Guobao Xiao","orcid":"https://orcid.org/0000-0003-2928-8100"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guobao Xiao","raw_affiliation_strings":["School of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2928-8100","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4322","last_page":"4330"},"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/T11019","display_name":"Image Enhancement Techniques","score":0.9918000102043152,"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":0.9850000143051147,"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":0.6583945155143738},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5964639186859131},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.551264226436615},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5505082607269287},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5400375723838806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5070610046386719},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.357206791639328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2370249629020691},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21059629321098328},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.14496281743049622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583945155143738},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5964639186859131},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.551264226436615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5505082607269287},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5400375723838806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070610046386719},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.357206791639328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2370249629020691},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21059629321098328},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.14496281743049622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681119","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":[{"id":"https://metadata.un.org/sdg/13","score":0.550000011920929,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1994922096","https://openalex.org/W2943545929","https://openalex.org/W3131500599","https://openalex.org/W3164098653","https://openalex.org/W3173782971","https://openalex.org/W3177040887","https://openalex.org/W3203700770","https://openalex.org/W3204197760","https://openalex.org/W3206198586","https://openalex.org/W4213078714","https://openalex.org/W4214696292","https://openalex.org/W4226017195","https://openalex.org/W4281858881","https://openalex.org/W4285601297","https://openalex.org/W4312258849","https://openalex.org/W4312880622","https://openalex.org/W4315490105","https://openalex.org/W4360584634","https://openalex.org/W4365475024","https://openalex.org/W4386075673","https://openalex.org/W4388574886","https://openalex.org/W4391109864","https://openalex.org/W4391321061","https://openalex.org/W4391465821"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W2737719445","https://openalex.org/W4361279463","https://openalex.org/W4239098401","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W4387697615","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,88,106],"new":[4],"Segment":[5],"Anything":[6],"Model":[7],"with":[8,80,90,153,193],"Depth":[9],"Perception":[10],"(DSAM)":[11],"for":[12,126],"Camouflaged":[13],"Object":[14],"Detection":[15],"(COD).":[16],"DSAM":[17,133,180],"exploits":[18],"the":[19,29,35,39,49,55,75,81,97,130,135,139,146,162,187],"zero-shot":[20],"capability":[21],"of":[22,34,99,148,165,196],"SAM":[23,85,117,166],"to":[24,53,67,86,156],"realize":[25],"precise":[26],"segmentation":[27,163,183],"in":[28,71,84,113,129,171],"RGB-D":[30,141],"domain.":[31,132],"It":[32,109,144],"consists":[33],"Prompt-Deeper":[36,43],"Module":[37,44,52,95],"and":[38,48,60,122,167,185],"Finer":[40,94],"Module.":[41],"The":[42,93,199],"utilizes":[45],"knowledge":[46],"distillation":[47],"Bias":[50],"Correction":[51],"achieve":[54,157],"interaction":[56],"between":[57],"RGB":[58,72,154],"features":[59,66,77,150,155],"depth":[61,65,91,107,111,149],"features,":[62],"especially":[63],"using":[64],"correct":[68],"erroneous":[69],"parts":[70],"features.":[73],"Then,":[74],"interacted":[76],"are":[78],"combined":[79],"box":[82],"prompt":[83,89],"create":[87],"perception.":[92],"explores":[96],"possibility":[98],"accurately":[100],"segmenting":[101],"highly":[102],"camouflaged":[103],"targets":[104],"from":[105],"perspective.":[108],"uncovers":[110],"cues":[112],"areas":[114],"missed":[115],"by":[116],"through":[118],"mask":[119],"reversion,":[120],"self-filtering,":[121],"self-attention":[123],"operations,":[124],"compensating":[125],"its":[127,169],"defects":[128],"COD":[131,142,176,191],"represents":[134],"first":[136],"step":[137],"towards":[138],"SAM-based":[140],"model.":[143],"maximizes":[145],"utilization":[147],"while":[151],"synergizing":[152],"multimodal":[158],"complementarity,":[159],"thereby":[160],"overcoming":[161],"limitations":[164],"improving":[168],"accuracy":[170],"COD.":[172],"Experimental":[173],"results":[174],"on":[175,190],"benchmarks":[177,192],"demonstrate":[178],"that":[179],"achieves":[181],"excellent":[182],"performance":[184],"reaches":[186],"state-of-the-art":[188],"(SOTA)":[189],"less":[194],"consumption":[195],"training":[197],"resources.":[198],"code":[200],"will":[201],"be":[202],"available":[203],"at":[204],"https://github.com/guobaoxiao/DSAM.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":25}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}