{"id":"https://openalex.org/W7148562159","doi":"https://doi.org/10.48550/arxiv.2604.00784","title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","display_name":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148562159","doi":"https://doi.org/10.48550/arxiv.2604.00784"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.00784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.00784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008280968","display_name":"Lennart Maack","orcid":"https://orcid.org/0009-0002-0097-0157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maack, Lennart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087348362","display_name":"Alexander Schlaefer","orcid":"https://orcid.org/0000-0001-9201-8854"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schlaefer, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9215999841690063,"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":0.9215999841690063,"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":0.0210999995470047,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.013100000098347664,"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/pipeline","display_name":"Pipeline (software)","score":0.7049000263214111},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5213000178337097},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.47510001063346863},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42910000681877136},{"id":"https://openalex.org/keywords/surgical-procedures","display_name":"Surgical procedures","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016999959945679},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7049000263214111},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C3019611579","wikidata":"https://www.wikidata.org/wiki/Q6641956","display_name":"Surgical procedures","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.00784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.00784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46630164980888367,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Surgical":[0],"video":[1,106],"understanding":[2,160],"is":[3,49,168],"a":[4,71],"crucial":[5],"prerequisite":[6],"for":[7,86],"advancing":[8],"Computer-Assisted":[9],"Surgery.":[10],"While":[11],"vision-language":[12,25],"models":[13],"(VLMs)":[14],"have":[15],"recently":[16],"been":[17],"applied":[18],"to":[19,52,81,94,157],"the":[20,69,101,142,154],"surgical":[21,24,47,84,97,164],"domain,":[22],"existing":[23],"datasets":[26,39,85],"lack":[27],"in":[28,46,126,163],"capturing":[29],"and":[30,77],"evaluating":[31],"complex,":[32],"interleaved":[33],"spatial-temporal":[34,44,88,113,130,151,159],"dynamics.":[35],"Creating":[36],"large":[37,60],"scale":[38],"that":[40,120],"accurately":[41],"represent":[42],"fine-grained":[43,87,112],"relationships":[45],"videos":[48],"challenging":[50],"due":[51],"costly":[53],"manual":[54],"annotations":[55],"or":[56],"error-prone":[57],"generation":[58,73],"using":[59],"language":[61],"models.":[62],"To":[63],"address":[64],"this":[65,92],"gap,":[66],"we":[67,99],"introduce":[68],"SurgSTU-Pipeline,":[70],"deterministic":[72],"pipeline":[74,93],"featuring":[75],"temporal":[76],"spatial":[78],"continuity":[79],"filtering":[80],"reliably":[82],"create":[83,100],"multimodal":[89],"understanding.":[90],"Applying":[91],"publicly":[95],"available":[96,169],"datasets,":[98],"SurgSTU":[102,143],"dataset,":[103],"comprising":[104],"6711":[105],"clips":[107],"densely":[108],"extended":[109],"with":[110],"150k":[111],"question-answer":[114],"samples.":[115],"Our":[116],"comprehensive":[117],"evaluation":[118],"shows":[119],"while":[121],"state-of-the-art":[122],"generalist":[123],"VLMs":[124,162],"struggle":[125],"zero-shot":[127],"settings,":[128],"their":[129],"capabilities":[131],"can":[132],"be":[133],"improved":[134],"through":[135],"in-context":[136],"learning.":[137],"A":[138],"fine-tuned":[139],"VLM":[140],"on":[141],"training":[144],"dataset":[145],"achieves":[146],"highest":[147],"performance":[148],"among":[149],"all":[150],"tasks,":[152],"validating":[153],"dataset's":[155],"efficacy":[156],"improve":[158],"of":[161],"videos.":[165],"The":[166],"project":[167],"here:":[170],"https://lennart-maack.github.io/SurgSTU-project":[171]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-03T00:00:00"}