{"id":"https://openalex.org/W7162559482","doi":"https://doi.org/10.1109/tip.2026.3695410","title":"Neural Wave Propagation for Surgical Video Action Recognition: A New Dataset and Baseline","display_name":"Neural Wave Propagation for Surgical Video Action Recognition: A New Dataset and Baseline","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162559482","doi":"https://doi.org/10.1109/tip.2026.3695410","pmid":"https://pubmed.ncbi.nlm.nih.gov/42202188"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3695410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2026.3695410","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tip.2026.3695410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101579766","display_name":"Tianxiang Chen","orcid":"https://orcid.org/0000-0002-8059-3672"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianxiang Chen","raw_affiliation_strings":["Terminal Intelligence Computing Division, Alibaba Cloud., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7758-699X","affiliations":[{"raw_affiliation_string":"Terminal Intelligence Computing Division, Alibaba Cloud., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137109381","display_name":"Weibin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Wang","raw_affiliation_strings":["South China Normal University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137167363","display_name":"Zhentao Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I3087508612","display_name":"Pride Foundation","ror":"https://ror.org/05tewmz75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3087508612"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhentao Tan","raw_affiliation_strings":["reside, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"reside, Hangzhou, China","institution_ids":["https://openalex.org/I3087508612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038128014","display_name":"Ru Zhou","orcid":"https://orcid.org/0000-0001-9067-8920"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2801556517","display_name":"Ruijin Hospital","ror":"https://ror.org/01hv94n30","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2801556517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru Zhou","raw_affiliation_strings":["Department of General Surgery, Ruijin Hospital Luwan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9067-8920","affiliations":[{"raw_affiliation_string":"Department of General Surgery, Ruijin Hospital Luwan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I2801556517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137106632","display_name":"Yue Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I3087508612","display_name":"Pride Foundation","ror":"https://ror.org/05tewmz75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3087508612"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["reside, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"reside, Hangzhou, China","institution_ids":["https://openalex.org/I3087508612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137191764","display_name":"Ziyang Wang","orcid":"https://orcid.org/0000-0003-1605-0873"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ziyang Wang","raw_affiliation_strings":["School of Computer Science and Digital Technologies, Aston University, Birmingham, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1605-0873","affiliations":[{"raw_affiliation_string":"School of Computer Science and Digital Technologies, Aston University, Birmingham, U.K","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045227579","display_name":"Le L\u00fc","orcid":"https://orcid.org/0000-0002-6799-9416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Lu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076034720","display_name":"M X Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2801556517","display_name":"Ruijin Hospital","ror":"https://ror.org/01hv94n30","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2801556517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Wang","raw_affiliation_strings":["Department of General Surgery, Ruijin Hospital Luwan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of General Surgery, Ruijin Hospital Luwan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I2801556517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137103128","display_name":"Zi Ye","orcid":"https://orcid.org/0000-0003-1002-0315"},"institutions":[{"id":"https://openalex.org/I157286207","display_name":"National University of Ireland, Maynooth","ror":"https://ror.org/048nfjm95","country_code":"IE","type":"education","lineage":["https://openalex.org/I157286207"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Zi Ye","raw_affiliation_strings":["Department of Computer Science, Maynooth University, Maynooth, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-1002-0315","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Maynooth University, Maynooth, Ireland","institution_ids":["https://openalex.org/I157286207"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66383524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6744","last_page":"6759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.24089999496936798,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.24089999496936798,"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":0.16009999811649323,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.09690000116825104,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47690001130104065},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4426000118255615},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.42100000381469727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36329999566078186},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.33869999647140503},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3043999969959259},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.303600013256073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6313999891281128},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5914000272750854},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25220000743865967}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D010535","descriptor_name":"Laparoscopy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020535","descriptor_name":"Video-Assisted Surgery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2026.3695410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2026.3695410","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42202188","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42202188","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:publications.aston.ac.uk:49150","is_oa":true,"landing_page_url":null,"pdf_url":"https://publications.aston.ac.uk/id/eprint/49150/1/T_Chen_et_al_Neural_Wave_Propagation_for_Surgical_Video_Action_Recognition_A_New_Dataset_and_Baseline_AAM.pdf","source":{"id":"https://openalex.org/S4306400483","display_name":"Aston Publications Explorer (Aston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169199633","host_organization_name":"Aston University","host_organization_lineage":["https://openalex.org/I169199633"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1109/tip.2026.3695410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2026.3695410","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"and":[1,35,50,67,69,135,216],"efficient":[2],"recognition":[3,21,42,215,218],"of":[4,112],"surgical":[5,14,18,65,89,116,184,212],"actions":[6,126],"in":[7,52,87],"videos":[8],"is":[9,84,94,100,227,233],"critical":[10],"for":[11,63,80,123],"advancing":[12],"AI-driven":[13],"robotics.":[15],"However,":[16],"current":[17],"video":[19,41,117,161,213],"action":[20,37,214],"(SVAR)":[22],"datasets":[23,49],"suffer":[24],"from":[25],"limitations":[26],"such":[27],"as":[28,164],"small":[29],"scale,":[30],"low":[31],"resolution,":[32],"inconsistent":[33],"annotations,":[34],"insufficient":[36],"coverage.":[38],"Most":[39],"latest":[40],"models":[43],"are":[44],"trained":[45],"on":[46,149,190,210],"large-scale":[47],"common":[48],"underperform":[51],"SVAR":[53,110],"due":[54],"to":[55],"architectures":[56],"that":[57,168],"suppress":[58],"high-frequency":[59,183],"visual":[60],"details":[61],"(crucial":[62],"recognizing":[64],"tools":[66],"motions)":[68],"lack":[70],"a":[71,97,165],"strong":[72],"spatial":[73],"inductive":[74,158],"bias,":[75],"requiring":[76],"extensive":[77],"training":[78,192,205],"data":[79,92,137,200],"good":[81],"convergence.":[82],"This":[83,186],"particularly":[85],"challenging":[86],"the":[88],"domain,":[90],"where":[91],"access":[93],"limited.":[95],"Therefore,":[96],"new":[98],"baseline":[99,147],"required.":[101],"To":[102],"address":[103],"these":[104],"issues,":[105],"we":[106],"introduce":[107],"LapSurg-230K,":[108],"an":[109,145,155],"dataset":[111],"7,569":[113],"high-resolution":[114],"laparoscopic":[115],"clips":[118],"with":[119],"230,246":[120],"frames,":[121],"well-annotated":[122],"11":[124],"key":[125],"across":[127],"9":[128],"surgery":[129],"types.":[130],"It":[131],"supports":[132],"both":[133,211],"full":[134],"progressive":[136],"volume":[138],"evaluation":[139],"settings.":[140],"We":[141],"further":[142],"propose":[143],"WaveR,":[144],"attention-free":[146],"based":[148],"physical":[150,157],"wave":[151,166],"propagation.":[152],"WaveR":[153],"embeds":[154],"innate":[156],"bias:":[159],"each":[160],"patch":[162],"acts":[163],"source":[167],"propagates":[169],"waves":[170],"toward":[171],"action-critical":[172],"regions":[173],"(e.g.,":[174],"instrument":[175],"tips),":[176],"adaptively":[177],"aggregating":[178],"spatial-temporal":[179],"context":[180],"while":[181],"preserving":[182],"cues.":[185],"mechanism":[187],"eliminates":[188],"dependency":[189],"massive":[191],"data.":[193],"Experiments":[194],"demonstrate":[195],"WaveR's":[196],"robustness":[197],"under":[198,224],"extreme":[199],"scarcity":[201],"(":[202],"$\\leq":[203],"30\\%$":[204],"samples),":[206],"achieving":[207],"state-of-the-art":[208],"accuracy":[209],"phase":[217],"tasks.":[219],"The":[220],"complete":[221],"dataset,":[222],"licensed":[223],"CC-BY":[225],"4.0,":[226],"available":[228,234],"at":[229,235],"https://doi.org/10.6084/m9.figshare.32237319.":[230],"Our":[231],"code":[232],"https://github.com/yezizi1022/WaveR_TIP.":[236]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-28T00:00:00"}
