{"id":"https://openalex.org/W7138248267","doi":"https://doi.org/10.1609/aaai.v40i13.38027","title":"Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion","display_name":"Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138248267","doi":"https://doi.org/10.1609/aaai.v40i13.38027"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38027","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38027","pdf_url":null,"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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129734674","display_name":"Meng Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Meng Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049657236","display_name":"Kun Yuan","orcid":"https://orcid.org/0000-0002-6542-4483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677845","display_name":"Shi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743587","display_name":"Yue Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705786","display_name":"Long Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Bai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678610","display_name":"Nassir Navab","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nassir Navab","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735526","display_name":"Hongliang Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongliang Ren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657202","display_name":"Hong Joo Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong Joo Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129655719","display_name":"Tom Vercauteren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Vercauteren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129723553","display_name":"Nicolas Padoy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Padoy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129734674"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58928571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10548","last_page":"10556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5026000142097473,"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":0.5026000142097473,"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/T10916","display_name":"Surgical Simulation and Training","score":0.3758000135421753,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.03150000050663948,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/surgical-instrument","display_name":"Surgical instrument","score":0.7982000112533569},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5910000205039978},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5494999885559082},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5167999863624573},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47620001435279846},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3772999942302704},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C2778181360","wikidata":"https://www.wikidata.org/wiki/Q1074814","display_name":"Surgical instrument","level":2,"score":0.7982000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.699400007724762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6888999938964844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6438000202178955},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C3019611579","wikidata":"https://www.wikidata.org/wiki/Q6641956","display_name":"Surgical procedures","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C3017684034","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Surgical robot","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i13.38027","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38027","pdf_url":null,"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:arXiv.org:2601.12224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.12224","pdf_url":"https://arxiv.org/pdf/2601.12224","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38027","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38027","pdf_url":null,"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/G1190480411","display_name":null,"funder_award_id":"NS/A000049/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1322964166","display_name":null,"funder_award_id":"203148/Z/16/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G1536759560","display_name":null,"funder_award_id":"ANR-10-IAHU-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G170668223","display_name":"Computational Methods to Analyse Intra-operative Adverse Events in Surgery at Scale","funder_award_id":"101088553","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3335229504","display_name":null,"funder_award_id":"Avenir","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4215281196","display_name":null,"funder_award_id":"WT203148/Z/16/Z","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4536661056","display_name":"EPSRC Centre for Doctoral Training in Smart Medical Imaging at King's College London and Imperial College London","funder_award_id":"EP/S022104/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5907639349","display_name":null,"funder_award_id":"203148","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G5917232323","display_name":null,"funder_award_id":"WT203148/Z/16/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G6292774592","display_name":null,"funder_award_id":"NS/A000049/1","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G7240651115","display_name":null,"funder_award_id":"ANR-10","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8787748348","display_name":null,"funder_award_id":"203148/Z/16/Z","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Enabling":[0],"intuitive,":[1],"language-driven":[2,139],"interaction":[3],"with":[4,39,116],"surgical":[5,17,27,37,131,140],"scenes":[6],"is":[7],"a":[8,62,111,134],"critical":[9],"step":[10],"toward":[11],"intelligent":[12],"operating":[13],"rooms":[14],"and":[15,52,78,93,105,120,128],"autonomous":[16],"robotic":[18],"assistance.":[19],"However,":[20],"the":[21],"task":[22],"of":[23],"referring":[24],"segmentation,":[25],"localizing":[26],"instruments":[28,95],"based":[29],"on":[30,48],"natural":[31],"language":[32,69],"descriptions,":[33],"remains":[34],"underexplored":[35],"in":[36,71],"videos,":[38],"existing":[40],"approaches":[41],"struggling":[42],"to":[43,46,91],"generalize":[44],"due":[45],"reliance":[47],"static":[49],"visual":[50],"cues":[51],"predefined":[53],"instrument":[54,72],"names.":[55],"In":[56],"this":[57],"work,":[58],"we":[59,108],"introduce":[60],"SurgRef,":[61,107],"novel":[63],"motion-guided":[64],"framework":[65],"that":[66],"grounds":[67],"free-form":[68],"expressions":[70],"motion,":[73],"capturing":[74],"how":[75],"tools":[76],"move":[77],"interact":[79],"across":[80,130],"time,":[81],"rather":[82],"than":[83],"what":[84],"they":[85],"look":[86],"like.":[87],"This":[88],"allows":[89],"models":[90],"understand":[92],"segment":[94],"even":[96],"under":[97],"occlusion,":[98],"ambiguity,":[99],"or":[100],"unfamiliar":[101],"terminology.":[102],"To":[103],"train":[104],"evaluate":[106],"present":[109],"Ref-IMotion,":[110],"diverse,":[112],"multi-institutional":[113],"video":[114,141],"dataset":[115],"dense":[117],"spatiotemporal":[118],"masks":[119],"rich":[121],"motion-centric":[122],"expressions.":[123],"SurgRef":[124],"achieves":[125],"state-of-the-art":[126],"accuracy":[127],"generalization":[129],"procedures,":[132],"setting":[133],"new":[135],"benchmark":[136],"for":[137],"robust,":[138],"segmentation.":[142]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}
