{"id":"https://openalex.org/W4415061873","doi":"https://doi.org/10.1109/iccv51701.2025.02290","title":"Online Reasoning Video Segmentation with Just-in-Time Digital Twins","display_name":"Online Reasoning Video Segmentation with Just-in-Time Digital Twins","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415061873","doi":"https://doi.org/10.1109/iccv51701.2025.02290"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.21056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072622467","display_name":"Yiqing Shen","orcid":"https://orcid.org/0000-0001-7866-3339"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqing Shen","raw_affiliation_strings":["Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089731540","display_name":"Bohan Liu","orcid":"https://orcid.org/0009-0005-4338-9188"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bohan Liu","raw_affiliation_strings":["Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082289162","display_name":"Chenjia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenjia Li","raw_affiliation_strings":["Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111271054","display_name":"Lalithkumar Seenivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lalithkumar Seenivasan","raw_affiliation_strings":["Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087095414","display_name":"Mathias Unberath","orcid":"https://orcid.org/0000-0002-0055-9950"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathias Unberath","raw_affiliation_strings":["Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24698","last_page":"24706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9147999882698059,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9147999882698059,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.904699981212616,"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":0.5742999911308289},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5153999924659729},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.44209998846054077},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.43389999866485596},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42320001125335693},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.41130000352859497},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.3560999929904938},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.3555999994277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674000263214111},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426999926567078},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C2988454689","wikidata":"https://www.wikidata.org/wiki/Q173131","display_name":"Digital video","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.21056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21056","pdf_url":"https://arxiv.org/pdf/2503.21056","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2503.21056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21056","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.21056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21056","pdf_url":"https://arxiv.org/pdf/2503.21056","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reasoning":[0],"segmentation":[1,237],"(RS)":[2],"aims":[3],"to":[4,28,55,87,116,178,181,222],"identify":[5,223],"and":[6,93,132,199,255],"segment":[7],"objects":[8],"of":[9,48,68,97,146,164,206],"interest":[10],"based":[11],"on":[12,43,217],"implicit":[13,156,244],"text":[14,245],"queries.":[15,246],"As":[16],"such,":[17],"RS":[18,39,137],"is":[19,143],"a":[20,147,159,165,183,232],"catalyst":[21],"for":[22,106,134,196],"embodied":[23],"AI":[24],"agents,":[25],"enabling":[26],"them":[27],"interpret":[29],"high-level":[30,170],"commands":[31],"without":[32,138],"requiring":[33],"explicit":[34],"step-by-step":[35],"guidance.":[36],"However,":[37],"current":[38],"approaches":[40],"rely":[41],"heavily":[42],"the":[44,144,162,189,194],"visual":[45],"perception":[46,131],"capabilities":[47],"multimodal":[49],"large":[50],"language":[51],"models":[52],"(LLMs),":[53],"leading":[54],"several":[56],"major":[57],"limitations.":[58],"First,":[59],"they":[60,78,113],"struggle":[61],"with":[62,90,242,257],"queries":[63],"that":[64,72,129],"require":[65,84],"multiple":[66],"steps":[67],"reasoning":[69,133,216,236,251,260],"or":[70,109],"those":[71],"involve":[73],"complex":[74],"spatial/temporal":[75],"relationships.":[76],"Second,":[77],"necessitate":[79],"LLM":[80,139,160,190,213],"fine-tuning,":[81],"which":[82],"may":[83,94],"frequent":[85],"updates":[86],"maintain":[88],"compatibility":[89],"contemporary":[91],"LLMs":[92],"increase":[95],"risks":[96],"catastrophic":[98],"forgetting":[99],"during":[100],"fine-tuning.":[101,140],"Finally,":[102],"being":[103],"primarily":[104],"designed":[105],"static":[107],"images":[108],"offline":[110],"video":[111,118,136,171,235],"processing,":[112],"scale":[114],"poorly":[115],"online":[117,135],"data.":[119],"To":[120,226],"address":[121],"these":[122],"limitations,":[123],"we":[124,230],"propose":[125],"an":[126,155],"agent":[127],"framework":[128],"disentangles":[130],"Our":[141],"innovation":[142],"introduction":[145],"just-in-time":[148],"digital":[149,184,219],"twin":[150,185,220],"concept,":[151],"where":[152],"--":[153,158],"given":[154],"query":[157],"plans":[161],"construction":[163],"low-level":[166],"scene":[167],"representation":[168,221],"from":[169],"using":[172],"specialist":[173,210],"vision":[174],"models.":[175],"We":[176],"refer":[177],"this":[179,202,218],"approach":[180],"creating":[182],"as":[186],"\"just-in-time\"":[187],"because":[188],"planner":[191],"will":[192],"anticipate":[193],"need":[195],"specific":[197],"information":[198],"only":[200],"request":[201],"limited":[203],"subset":[204],"instead":[205],"always":[207],"evaluating":[208],"every":[209],"model.":[211],"The":[212,247],"then":[214],"performs":[215],"target":[224],"objects.":[225],"evaluate":[227],"our":[228],"approach,":[229],"introduce":[231],"new":[233],"comprehensive":[234],"benchmark":[238,248],"comprising":[239],"200":[240],"videos":[241],"895":[243],"spans":[249],"three":[250,258],"categories":[252],"(semantic,":[253],"spatial,":[254],"temporal)":[256],"different":[259],"chain":[261],"complexity.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-11T00:00:00"}