{"id":"https://openalex.org/W7137945989","doi":"https://doi.org/10.1609/aaai.v40i16.38413","title":"Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory","display_name":"Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137945989","doi":"https://doi.org/10.1609/aaai.v40i16.38413"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i16.38413","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38413","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38413/42375","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38413/42375","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127963145","display_name":"Zhengtong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengtong Zhu","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666401","display_name":"Jiaqing Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqing Fan","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125934586","display_name":"Zhixuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixuan Liu","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129749155","display_name":"Fanzhang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanzhang Li","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"14022","last_page":"14030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.913100004196167,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.913100004196167,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.035999998450279236,"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":0.02410000003874302,"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":0.7052000164985657},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5302000045776367},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47380000352859497},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4528999924659729},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4528000056743622},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4302000105381012},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.41659998893737793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7720999717712402},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6754000186920166},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5302000045776367},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4528999924659729},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4528000056743622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.41659998893737793},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2667999863624573},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i16.38413","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38413","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38413/42375","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38413","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38413","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38413","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38413/42375","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1987493015","display_name":null,"funder_award_id":"2018YFA0701701","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3162858518","display_name":null,"funder_award_id":"62176172","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5179993042","display_name":null,"funder_award_id":"2018YFA0701701","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8971729561","display_name":"\u591a\u6e90\u6570\u636e\u878d\u5408\u7684\u8868\u793a\u4e0e\u5b66\u4e60\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61672364","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324720","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137945989.pdf","grobid_xml":"https://content.openalex.org/works/W7137945989.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reasoning":[0,71],"Video":[1,72],"Object":[2,76,104],"Segmentation":[3,73],"(ReasonVOS)":[4],"is":[5],"a":[6,83],"challenging":[7],"task":[8],"that":[9,89,107],"requires":[10],"stable":[11,127,156],"object":[12,151],"segmentation":[13,33,87,139],"across":[14],"video":[15,86,119],"sequences":[16],"using":[17,95],"implicit":[18],"and":[19,109,138,173],"complex":[20],"textual":[21],"inputs.":[22],"Previous":[23],"methods":[24,42,92],"fine-tune":[25],"Multimodal":[26],"Large":[27],"Language":[28],"Models":[29],"(MLLMs)":[30],"to":[31,59,81,154],"produce":[32],"outputs,":[34],"which":[35,51],"demand":[36],"substantial":[37],"resources.":[38],"Additionally,":[39],"some":[40,60],"existing":[41,91],"are":[43],"coupled":[44],"in":[45,117,144],"the":[46,53,57,131,145],"processing":[47],"of":[48,56,140],"spatio-temporal":[49],"information,":[50],"affects":[52],"temporal":[54,128,146,152],"stability":[55],"model":[58],"extent.":[61],"To":[62],"address":[63],"these":[64],"issues,":[65],"we":[66,100,122,134,148],"propose":[67,101,123],"Training-Free":[68],"Spatio-temporal":[69,124],"Decoupled":[70],"with":[74],"Adaptive":[75,103],"Memory":[77,105],"(SDAM).":[78],"We":[79],"aim":[80],"design":[82],"training-free":[84],"reasoning":[85],"framework":[88],"outperforms":[90],"requiring":[93],"fine-tuning,":[94],"only":[96],"pre-trained":[97],"models.":[98],"Meanwhile,":[99],"an":[102],"module":[106],"selects":[108],"memorizes":[110],"key":[111,150],"objects":[112],"based":[113],"on":[114,164],"motion":[115],"cues":[116],"different":[118],"sequences.":[120],"Finally,":[121],"Decoupling":[125],"for":[126],"propagation.":[129,158],"In":[130],"spatial":[132],"domain,":[133,147],"achieve":[135],"precise":[136],"localization":[137],"target":[141],"objects,":[142],"while":[143],"leverage":[149],"information":[153],"drive":[155],"cross-frame":[157],"Our":[159],"method":[160],"achieves":[161],"excellent":[162],"results":[163],"five":[165],"benchmark":[166],"datasets,":[167],"including":[168],"Ref-YouTubeVOS,":[169],"Ref-DAVIS17,":[170],"MeViS,":[171],"ReasonVOS,":[172],"ReVOS.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}