{"id":"https://openalex.org/W7203829038","doi":"https://doi.org/10.1109/access.2026.3725803","title":"Temporal Stride as an Inductive Bias in Masked Video Pretraining for Endoscopic Video Analysis","display_name":"Temporal Stride as an Inductive Bias in Masked Video Pretraining for Endoscopic Video Analysis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7203829038","doi":"https://doi.org/10.1109/access.2026.3725803"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3725803","doi":"https://doi.org/10.1109/access.2026.3725803","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3725803","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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 Access","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3725803","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102717023","display_name":"A. T. M. Taha","orcid":"https://orcid.org/0009-0006-6346-4162","observed_orcids":["https://orcid.org/0009-0006-6346-4162"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ahmad Taha","raw_affiliation_strings":["Research Center of the Artificial Intelligence Institute, Innopolis University"],"raw_orcid":"https://orcid.org/0009-0006-6346-4162","affiliations":[{"raw_affiliation_string":"Research Center of the Artificial Intelligence Institute, Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079013160","display_name":"Rustam Lukmanov","orcid":"https://orcid.org/0000-0001-9257-7410","observed_orcids":["https://orcid.org/0000-0001-9257-7410"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Rustam A. Lukmanov","raw_affiliation_strings":["Research Center of the Artificial Intelligence Institute, Innopolis University"],"raw_orcid":"https://orcid.org/0000-0001-9257-7410","affiliations":[{"raw_affiliation_string":"Research Center of the Artificial Intelligence Institute, Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116741"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"136401","last_page":"136445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.49239999055862427,"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":0.49239999055862427,"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":0.10429999977350235,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08659999817609787,"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/inductive-bias","display_name":"inductive bias","score":0.8199999928474426},{"id":"https://openalex.org/keywords/videomae","display_name":"VideoMAE","score":0.8019999861717224},{"id":"https://openalex.org/keywords/endoscopic-video-analysis","display_name":"endoscopic video analysis","score":0.8709999918937683},{"id":"https://openalex.org/keywords/colonoscopy","display_name":"colonoscopy","score":0.9010000228881836},{"id":"https://openalex.org/keywords/laparoscopic-surgery","display_name":"laparoscopic surgery","score":0.9829999804496765},{"id":"https://openalex.org/keywords/polyp-detection","display_name":"polyp detection","score":0.8199999928474426},{"id":"https://openalex.org/keywords/surgical-action-recognition","display_name":"surgical action recognition","score":0.9919999837875366},{"id":"https://openalex.org/keywords/spectral-bias","display_name":"spectral bias","score":0.8429999947547913},{"id":"https://openalex.org/keywords/attention-patterns","display_name":"attention patterns","score":0.593999981880188},{"id":"https://openalex.org/keywords/arrow-of-time","display_name":"arrow of time","score":0.7149999737739563},{"id":"https://openalex.org/keywords/temporal-dynamics","display_name":"temporal dynamics","score":0.3499999940395355},{"id":"https://openalex.org/keywords/information-theoretic-analysis","display_name":"information-theoretic analysis","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552000284194946},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6086999773979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410000085830688},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C18007350","wikidata":"https://www.wikidata.org/wiki/Q7394815","display_name":"STRIDE","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C164781476","wikidata":"https://www.wikidata.org/wiki/Q727477","display_name":"S-Video","level":5,"score":0.26499998569488525},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3725803","doi":"https://doi.org/10.1109/access.2026.3725803","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3725803","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c53338e7823347058669bf39343bf77b","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/c53338e7823347058669bf39343bf77b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"IEEE Access, Vol 14, Pp 136401-136445 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3725803","doi":"https://doi.org/10.1109/access.2026.3725803","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3725803","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W33507944","https://openalex.org/W343636949","https://openalex.org/W1541507378","https://openalex.org/W1996118086","https://openalex.org/W2029732115","https://openalex.org/W2100967164","https://openalex.org/W2122922389","https://openalex.org/W2478708596","https://openalex.org/W2625366777","https://openalex.org/W2626778328","https://openalex.org/W2799087757","https://openalex.org/W2990503944","https://openalex.org/W2994536315","https://openalex.org/W3036988171","https://openalex.org/W3156973125","https://openalex.org/W3175413674","https://openalex.org/W3178823375","https://openalex.org/W3200130628","https://openalex.org/W3202715235","https://openalex.org/W3203828408","https://openalex.org/W3214192224","https://openalex.org/W3216270236","https://openalex.org/W4223948957","https://openalex.org/W4226002507","https://openalex.org/W4312312750","https://openalex.org/W4312804044","https://openalex.org/W4313009245","https://openalex.org/W4321486452","https://openalex.org/W4376631152","https://openalex.org/W4385379973","https://openalex.org/W4385570922","https://openalex.org/W4386057769","https://openalex.org/W4386065386","https://openalex.org/W4386071576","https://openalex.org/W4387225560","https://openalex.org/W4387225742","https://openalex.org/W4389104669","https://openalex.org/W4390874131","https://openalex.org/W4392698767","https://openalex.org/W4393158550","https://openalex.org/W4399021842","https://openalex.org/W4403583435","https://openalex.org/W4404115643","https://openalex.org/W4405090109","https://openalex.org/W4406313381","https://openalex.org/W4407450062","https://openalex.org/W4409261926","https://openalex.org/W4412444881","https://openalex.org/W4413147749","https://openalex.org/W4413275066","https://openalex.org/W4415539738","https://openalex.org/W4415796150","https://openalex.org/W4416353841","https://openalex.org/W7117108071","https://openalex.org/W7126041641","https://openalex.org/W7127584095","https://openalex.org/W7131233286","https://openalex.org/W7133204854","https://openalex.org/W7133229819","https://openalex.org/W7133239857","https://openalex.org/W7140047993","https://openalex.org/W7149264645","https://openalex.org/W7160071208"],"related_works":["https://openalex.org/W4390874131","https://openalex.org/W4387969684","https://openalex.org/W7133229819","https://openalex.org/W4415795404","https://openalex.org/W6948471897","https://openalex.org/W4386185599","https://openalex.org/W4417461707","https://openalex.org/W4386076203","https://openalex.org/W4397026222","https://openalex.org/W4386076625"],"abstract_inverted_index":{"Temporal":[0],"stride":[1,57,135,178,212,233],"is":[2,19,53,75,173,209],"usually":[3],"treated":[4],"as":[5,158],"a":[6,21,32,123],"compute":[7],"setting":[8],"in":[9],"masked":[10,202],"video":[11,41,203],"modeling,":[12],"but":[13],"this":[14,177],"study":[15,34],"shows":[16],"that":[17,25,55,176,193,237],"it":[18,52],"actually":[20],"major":[22],"design":[23],"choice":[24],"selects":[26],"between":[27,134],"different":[28],"useful":[29],"biases.":[30],"In":[31],"controlled":[33],"with":[35,130],"VideoMAE":[36],"v2":[37],"on":[38,63,69,214,239],"two":[39],"clinical":[40,83],"datasets,":[42],"REAL-Colon":[43],"for":[44,49,99,108,224,235],"diagnostic":[45],"colonoscopy":[46],"and":[47,93,107,136,165,227,231],"GynSurg":[48],"laparoscopic":[50],"surgery,":[51],"observed":[54,77],"increasing":[56],"shifts":[58],"the":[59,137,144,150,161,182,188,194,215,219],"encoder":[60],"from":[61,102,112,181,187],"focusing":[62,68],"high-frequency,":[64],"texture-based":[65],"details":[66],"to":[67,105,115,154,210],"lower-frequency,":[70],"shape-based":[71],"structure.":[72],"This":[73],"change":[74],"consistently":[76],"across":[78,127,201],"multiple":[79],"analyses,":[80],"including":[81],"downstream":[82],"separability,":[84],"attention":[85],"patterns,":[86],"manifold":[87],"structure,":[88],"spectral":[89],"bias,":[90],"token":[91],"behavior,":[92],"temporal":[94,128,156,216,240],"dynamics.":[95],"Probing":[96],"performance":[97],"improves":[98],"polyp":[100],"detection":[101,226],"F":[103,113],"$1=0.659$":[104],"0.713,":[106],"surgical":[109,228],"action":[110],"recognition":[111],"$1=0.411$":[114],"0.507.":[116],"Across":[117],"both":[118],"datasets":[119],"these":[120],"improvements":[121],"follow":[122],"consistent":[124],"monotonic":[125],"trend":[126],"strides,":[129],"Kendall":[131],"rank":[132],"correlations":[133],"primary":[138],"metrics":[139],"reaching":[140],"+":[141],"1.00.":[142],"At":[143],"same":[145,195],"time,":[146],"sparse":[147,221],"pretraining":[148],"makes":[149],"model":[151],"less":[152],"sensitive":[153],"fine":[155],"continuity,":[157],"shown":[159],"by":[160],"Arrow":[162],"of":[163,218],"Time":[164],"Out-of-Order":[166],"Frame":[167],"Localization":[168],"tasks.":[169],"An":[170],"information-theoretic":[171],"argument":[172],"also":[174],"provided":[175],"effect":[179,196],"comes":[180],"input":[183],"data":[184],"distribution,":[185],"not":[186],"reconstruction":[189],"target,":[190],"which":[191],"suggests":[192],"should":[197],"apply":[198],"more":[199],"broadly":[200],"modeling":[204],"methods.":[205],"The":[206],"practical":[207],"recommendation":[208],"choose":[211],"based":[213],"scale":[217],"task:":[220],"strides":[222],"(16-30)":[223],"pathology":[225],"phase":[229],"recognition,":[230],"dense":[232],"(1-8)":[234],"tasks":[236],"depend":[238],"causality.":[241]},"counts_by_year":[],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2026-08-21T00:00:00"}