{"id":"https://openalex.org/W4399418527","doi":"https://doi.org/10.1145/3652583.3658036","title":"RGB-D Video Object Segmentation via Enhanced Multi-store Feature Memory","display_name":"RGB-D Video Object Segmentation via Enhanced Multi-store Feature Memory","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418527","doi":"https://doi.org/10.1145/3652583.3658036"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658036","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101805346","display_name":"Boyue Xu","orcid":"https://orcid.org/0009-0003-7697-9630"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boyue Xu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-7697-9630","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906482","display_name":"Ruichao Hou","orcid":"https://orcid.org/0000-0001-8111-7339"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichao Hou","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8111-7339","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3092-424X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1391-1762","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101805346"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.4762,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61357422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1016","last_page":"1024"},"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":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9997000098228455,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8028070330619812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990997433662415},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7532729506492615},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7318728566169739},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7193306684494019},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5411656498908997},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5291369557380676},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5147061944007874},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5098646879196167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.507290780544281},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5070486068725586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4432436227798462},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41107556223869324},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0630650520324707}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8028070330619812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990997433662415},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7532729506492615},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7318728566169739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7193306684494019},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5411656498908997},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5291369557380676},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5147061944007874},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5098646879196167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.507290780544281},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5070486068725586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4432436227798462},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41107556223869324},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0630650520324707},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3652583.3658036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658036","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.16471","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.16471","pdf_url":"https://arxiv.org/pdf/2504.16471","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658036","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4388298099","display_name":null,"funder_award_id":"021714380026","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7458595415","display_name":null,"funder_award_id":"62072232","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/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418527.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2030007850","https://openalex.org/W2066278386","https://openalex.org/W2435777129","https://openalex.org/W2610147486","https://openalex.org/W2769833683","https://openalex.org/W2912429050","https://openalex.org/W2963983744","https://openalex.org/W3033114334","https://openalex.org/W3080837329","https://openalex.org/W3167186358","https://openalex.org/W4247924304","https://openalex.org/W4280526073","https://openalex.org/W4308621049","https://openalex.org/W4312396403","https://openalex.org/W4319999824","https://openalex.org/W4380884766","https://openalex.org/W4382240192","https://openalex.org/W4386159994","https://openalex.org/W4390479027","https://openalex.org/W6601048975"],"related_works":["https://openalex.org/W3144569342","https://openalex.org/W2185902295","https://openalex.org/W2945274617","https://openalex.org/W2372421320","https://openalex.org/W2057775483","https://openalex.org/W2041871225","https://openalex.org/W2386644571","https://openalex.org/W4205800335","https://openalex.org/W2387793296","https://openalex.org/W1558398159"],"abstract_inverted_index":{"The":[0],"RGB-Depth":[1],"(RGB-D)":[2],"Video":[3],"Object":[4],"Segmentation":[5,92],"(VOS)":[6],"aims":[7],"to":[8,35,96,107,128],"integrate":[9],"the":[10,17,25,68,91,98,139,146],"fine-grained":[11],"texture":[12],"information":[13,39],"of":[14,21,27],"RGB":[15],"with":[16],"spatial":[18],"geometric":[19],"clues":[20],"depth":[22],"modality,":[23],"boosting":[24],"performance":[26,144],"segmentation.":[28,64],"However,":[29],"off-the-shelf":[30],"RGB-D":[31,55,133,148],"segmentation":[32,85,99,110],"methods":[33],"fail":[34],"fully":[36],"explore":[37],"cross-modal":[38],"and":[40,72,116,121],"suffer":[41],"from":[42,78],"object":[43],"drift":[44],"during":[45],"long-term":[46],"prediction.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,66,82],"propose":[52],"a":[53,84],"novel":[54],"VOS":[56,149],"method":[57,141],"via":[58],"multi-store":[59],"feature":[60],"memory":[61,106],"for":[62],"robust":[63],"Specifically,":[65],"design":[67],"hierarchical":[69],"modality":[70,117],"selection":[71],"fusion,":[73],"which":[74],"adaptively":[75],"combines":[76],"features":[77],"both":[79],"modalities.":[80],"Additionally,":[81],"develop":[83],"refinement":[86],"module":[87],"that":[88,138],"effectively":[89],"utilizes":[90],"Anything":[93],"Model":[94],"(SAM)":[95],"refine":[97],"mask,":[100],"ensuring":[101],"more":[102],"reliable":[103],"results":[104,136],"as":[105],"guide":[108],"subsequent":[109],"tasks.":[111],"By":[112],"leveraging":[113],"spatio-temporal":[114],"embedding":[115],"embedding,":[118],"mixed":[119],"prompts":[120],"fused":[122],"images":[123],"are":[124],"fed":[125],"into":[126],"SAM":[127],"unleash":[129],"its":[130],"potential":[131],"in":[132],"VOS.":[134],"Experimental":[135],"show":[137],"proposed":[140],"achieves":[142],"state-of-the-art":[143],"on":[145],"latest":[147],"benchmark.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}