{"id":"https://openalex.org/W4415708648","doi":"https://doi.org/10.1109/icme59968.2025.11209420","title":"SAM2-Cap: Segment Anything 2 with using Parts and Object Spatial Hierarchical Relationships for Image Segmentation","display_name":"SAM2-Cap: Segment Anything 2 with using Parts and Object Spatial Hierarchical Relationships for Image Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708648","doi":"https://doi.org/10.1109/icme59968.2025.11209420"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100735904","display_name":"Xiufeng Liu","orcid":"https://orcid.org/0000-0002-3315-8571"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiufeng Liu","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019923","display_name":"Zhongqiu Zhao","orcid":"https://orcid.org/0000-0003-3940-3256"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqiu Zhao","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591010","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0009-7760-333X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010997479","display_name":"Donghui Hu","orcid":"https://orcid.org/0000-0001-9517-9688"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghui Hu","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101828632","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0002-3271-7482"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26563162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8460999727249146,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8460999727249146,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05400000140070915,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.018200000748038292,"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/segmentation","display_name":"Segmentation","score":0.7545999884605408},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6610999703407288},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.6050000190734863},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.592199981212616},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5598999857902527},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42170000076293945}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8260999917984009},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7545999884605408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544999718666077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7350000143051147},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6610999703407288},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.6050000190734863},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.592199981212616},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C42314347","wikidata":"https://www.wikidata.org/wiki/Q6865488","display_name":"Minimum spanning tree-based segmentation","level":5,"score":0.3707999885082245},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":34,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2021088830","https://openalex.org/W2049522781","https://openalex.org/W2106033751","https://openalex.org/W2285968993","https://openalex.org/W2526050071","https://openalex.org/W2560328367","https://openalex.org/W2765811365","https://openalex.org/W2884367402","https://openalex.org/W2956887593","https://openalex.org/W2964159205","https://openalex.org/W2981689412","https://openalex.org/W2981807748","https://openalex.org/W2991471181","https://openalex.org/W3034958977","https://openalex.org/W3086039674","https://openalex.org/W3092344722","https://openalex.org/W3095569631","https://openalex.org/W3096165964","https://openalex.org/W3100816363","https://openalex.org/W3132455321","https://openalex.org/W3159637683","https://openalex.org/W3196075503","https://openalex.org/W3203497085","https://openalex.org/W3211490618","https://openalex.org/W4213019189","https://openalex.org/W4252298411","https://openalex.org/W4281629935","https://openalex.org/W4310330006","https://openalex.org/W4360981268","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4402980496","https://openalex.org/W4405270558"],"related_works":[],"abstract_inverted_index":{"Image":[0],"segmentation":[1,27,67,136,155],"has":[2,51],"found":[3],"widespread":[4],"applications":[5],"in":[6,10,69,80],"computer":[7],"vision,":[8],"particularly":[9],"fields":[11],"such":[12],"as":[13,23],"medical":[14],"image":[15,57],"analysis,":[16],"autonomous":[17],"driving,":[18],"and":[19,47,111,120,129,135,156],"video":[20],"surveillance.":[21],"However,":[22,59],"the":[24,37,54,70,77,93,102,113,118,124,133,143],"complexity":[25],"of":[26,56,72,95,105,126,138],"tasks":[28],"increases,":[29],"new":[30],"vision":[31],"foundation":[32],"models":[33],"have":[34],"emerged,":[35],"notably":[36],"Segment":[38],"Anything":[39],"Model":[40],"(SAM)":[41],"series.":[42],"By":[43],"leveraging":[44],"large-scale":[45],"training":[46],"cross-domain":[48],"generalization,":[49],"SAM2":[50,63,96],"significantly":[52],"enhanced":[53],"performance":[55,79],"segmentation.":[58],"despite":[60],"these":[61,81],"advancements,":[62],"still":[64],"generates":[65],"class-agnostic":[66],"results":[68,164],"absence":[71],"manual":[73],"prompts.":[74],"To":[75],"enhance":[76],"SAM2's":[78],"scenarios,":[82],"we":[83,91],"propose":[84],"an":[85],"effective":[86],"framework,":[87],"termed":[88],"SAM2-Cap.":[89],"Specifically,":[90],"integrate":[92],"backbone":[94],"with":[97],"a":[98],"Capsule":[99],"Autoencoder,":[100],"exploiting":[101],"inherent":[103],"properties":[104],"capsule":[106],"networks":[107],"to":[108,166],"effectively":[109],"capture":[110],"decode":[112],"spatial":[114,130],"hierarchical":[115],"relationships":[116],"between":[117],"parts":[119],"objects.":[121],"This":[122],"improves":[123],"modeling":[125],"object":[127],"shapes":[128],"relationships,":[131],"enhancing":[132],"understanding":[134],"accuracy":[137],"complex":[139],"objects":[140],"while":[141],"reducing":[142],"reliance":[144],"on":[145,150],"prompt":[146],"information.":[147],"Extensive":[148],"experiments":[149],"Prostate":[151],"MRI":[152],"segmentation,":[153],"Polyp":[154],"Cityscapes":[157],"dataset,":[158],"demonstrate":[159],"our":[160],"method":[161],"achieves":[162],"competitive":[163],"compared":[165],"state-of-the-art":[167],"models.":[168]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}