{"id":"https://openalex.org/W7126020382","doi":"https://doi.org/10.1109/bibm66473.2025.11356430","title":"Multi-Task Learning for Optical Flow-Guided Self-Supervised Depth Estimation and Semantic Segmentation in Endoscopic Surgery","display_name":"Multi-Task Learning for Optical Flow-Guided Self-Supervised Depth Estimation and Semantic Segmentation in Endoscopic Surgery","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126020382","doi":"https://doi.org/10.1109/bibm66473.2025.11356430"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047293550","display_name":"Xuexin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuexin Jiang","raw_affiliation_strings":["Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090196175","display_name":"Dawei Lu","orcid":"https://orcid.org/0000-0001-8526-3739"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Lu","raw_affiliation_strings":["Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080643359","display_name":"Sifan Cao","orcid":"https://orcid.org/0009-0007-8388-5404"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Cao","raw_affiliation_strings":["Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124217980","display_name":"Long Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Shao","raw_affiliation_strings":["Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124277079","display_name":"Jingfan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfan Fan","raw_affiliation_strings":["Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404947","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-4801-7162"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Engineering Research Center of Mixed Reality and Advanced Display, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047293550"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68971471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5463","last_page":"5469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.7400000095367432,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.7400000095367432,"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":0.07280000299215317,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0215000007301569,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7336999773979187},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5996999740600586},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5879999995231628},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5257999897003174},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5184000134468079},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46230000257492065},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4318999946117401},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.383899986743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784500002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7415000200271606},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7336999773979187},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5996999740600586},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5879999995231628},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5415999889373779},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.32339999079704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2816999852657318},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G27375415","display_name":null,"funder_award_id":"2023YFC2415300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5168330297","display_name":null,"funder_award_id":"L222149","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2266464013","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2587989515","https://openalex.org/W2609883120","https://openalex.org/W2792472361","https://openalex.org/W2799124825","https://openalex.org/W2890949887","https://openalex.org/W2895340641","https://openalex.org/W2910628332","https://openalex.org/W2914872565","https://openalex.org/W2916798096","https://openalex.org/W2963150697","https://openalex.org/W2963548592","https://openalex.org/W2964309882","https://openalex.org/W2985775862","https://openalex.org/W3007768125","https://openalex.org/W3089762353","https://openalex.org/W3108178121","https://openalex.org/W3159637683","https://openalex.org/W3180638445","https://openalex.org/W3196904463","https://openalex.org/W4200072305","https://openalex.org/W4206573688","https://openalex.org/W4293363567","https://openalex.org/W4303649515","https://openalex.org/W4367319981","https://openalex.org/W4383108531","https://openalex.org/W4389625276","https://openalex.org/W4391323824","https://openalex.org/W4391876922","https://openalex.org/W4393935425","https://openalex.org/W4409984939"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,72,91],"in":[2,18],"surgical":[3],"scenes":[4],"requires":[5],"precise":[6],"differentiation":[7],"of":[8,24,31,130],"organs":[9],"and":[10,38,50,69,86,108,121,128],"tissues,":[11],"as":[12,14,100],"well":[13],"strong":[15],"generalization":[16],"capabilities":[17],"complex":[19],"environments,":[20],"while":[21],"the":[22,25,90,119,122,126],"training":[23],"model":[26],"demands":[27],"a":[28,43,75],"large":[29],"number":[30],"labeled":[32],"images.":[33],"To":[34],"address":[35],"these":[36],"challenges":[37],"improve":[39,70],"efficiency,":[40],"we":[41],"propose":[42],"joint-learning":[44],"framework":[45],"for":[46],"self-supervised":[47],"depth":[48,65],"estimation":[49,66],"semantic":[51,71,110],"segmentation,":[52],"enhanced":[53],"by":[54],"optical":[55,81],"flow.":[56],"Our":[57],"approach":[58],"effectively":[59],"leverages":[60],"high-dimensional":[61],"input":[62],"features,":[63],"using":[64],"to":[67,103],"guide":[68],"performance":[73],"at":[74],"lower":[76],"labeling":[77],"cost.":[78],"Meanwhile,":[79],"an":[80],"flow":[82],"module":[83],"is":[84],"introduced":[85],"jointly":[87],"trained":[88],"with":[89,93,97],"network,":[92],"its":[94],"outputs":[95],"fused":[96],"RGB":[98],"images":[99],"multimodal":[101],"inputs":[102],"enhance":[104],"dynamic":[105],"feature":[106],"perception":[107],"exploit":[109],"cues":[111],"from":[112],"motion.":[113],"We":[114],"evaluate":[115],"our":[116,131],"method":[117],"on":[118],"CholecSeg8k":[120],"experimental":[123],"results":[124],"demonstrate":[125],"effectiveness":[127],"robustness":[129],"proposed":[132],"approach.":[133]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-30T00:00:00"}