{"id":"https://openalex.org/W7160303601","doi":"https://doi.org/10.1109/wacv61042.2026.00822","title":"Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting","display_name":"Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160303601","doi":"https://doi.org/10.1109/wacv61042.2026.00822"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5091977067","display_name":"Rishikesh Bhyri","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishikesh Bhyri","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083164928","display_name":"Brian R. Quaranto","orcid":"https://orcid.org/0000-0003-2892-6932"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian R Quaranto","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7324-7034"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135399966","display_name":"Peter C W Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter C W Kim","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010864350","display_name":"Nan Xi","orcid":"https://orcid.org/0000-0002-7334-7772"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Xi","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65113739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8521","last_page":"8530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.4237000048160553,"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"}},"topics":[{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.4237000048160553,"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"}},{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.1923000067472458,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.03150000050663948,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3188999891281128},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2630999982357025},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.26260000467300415},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2565999925136566},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.2410999983549118}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6247000098228455},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5356000065803528},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2410999983549118},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.23899999260902405},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2296999990940094}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1003853626","https://openalex.org/W1985805934","https://openalex.org/W2121864252","https://openalex.org/W2150123015","https://openalex.org/W2158437588","https://openalex.org/W2347064614","https://openalex.org/W2520723410","https://openalex.org/W2884561390","https://openalex.org/W3138516171","https://openalex.org/W4213430315","https://openalex.org/W4312651322","https://openalex.org/W4388186341","https://openalex.org/W4390873375","https://openalex.org/W4390875025","https://openalex.org/W4393158196","https://openalex.org/W4402703087","https://openalex.org/W4402726935","https://openalex.org/W4402727478","https://openalex.org/W4402727874","https://openalex.org/W4402780099","https://openalex.org/W4403888306","https://openalex.org/W4413145978","https://openalex.org/W7103755574","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"counting":[1,30,62,149],"of":[2,22,104,167],"surgical":[3,124,136,169],"instruments":[4,32,41],"in":[5,37,95,163],"Operating":[6],"Rooms":[7],"(OR)":[8],"is":[9,78,176],"a":[10,52,66,89,130],"critical":[11],"prerequisite":[12],"for":[13,148],"ensuring":[14],"patient":[15],"safety":[16],"during":[17],"surgery.":[18],"Despite":[19],"recent":[20],"progress":[21],"large":[23],"visual-language":[24],"models":[25,116],"and":[26,174],"agentic":[27],"AI,":[28],"accurately":[29],"such":[31],"remains":[33],"highly":[34],"challenging,":[35],"particularly":[36],"dense":[38,168],"scenarios":[39],"where":[40],"are":[42],"tightly":[43],"clustered.":[44],"To":[45,98],"address":[46],"this":[47],"problem,":[48],"we":[49,108],"introduce":[50,109],"Chain-of-Look,":[51],"novel":[53],"visual":[54,68,81,106],"reasoning":[55],"framework":[56],"that":[57,142],"mimics":[58],"the":[59,84,101,105,110,117,164],"sequential":[60],"human":[61],"process":[63],"by":[64],"enforcing":[65],"structured":[67],"chain,":[69,107],"rather":[70],"than":[71],"relying":[72],"on":[73],"classic":[74],"object":[75],"detection":[76],"which":[77,114],"unordered.":[79],"This":[80],"chain":[82],"guides":[83],"model":[85],"to":[86,121],"count":[87],"along":[88],"coherent":[90],"spatial":[91,118],"trajectory,":[92],"improving":[93],"accuracy":[94],"complex":[96],"scenes.":[97],"further":[99],"enforce":[100],"physical":[102],"plausibility":[103],"neighboring":[111],"loss":[112],"function,":[113],"explicitly":[115],"constraints":[119],"inherent":[120],"densely":[122],"packed":[123],"instruments.":[125],"We":[126],"also":[127],"present":[128],"SurgCount-HD,":[129],"new":[131],"dataset":[132,175],"comprising":[133],"1,464":[134],"high-density":[135],"instrument":[137,170],"images.":[138],"Extensive":[139],"experiments":[140],"demonstrate":[141],"our":[143],"method":[144],"outperforms":[145],"state-of-the-art":[146],"approaches":[147],"(e.g.,":[150,160],"CountGD,":[151],"REC)":[152],"as":[153,155],"well":[154],"Multimodality":[156],"Large":[157],"Language":[158],"Models":[159],"Qwen,":[161],"ChatGPT)":[162],"challenging":[165],"task":[166],"counting.":[171],"The":[172],"code":[173],"available":[177],"at":[178],"https://github.com/rishi1134/CoLSR.git":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}