{"id":"https://openalex.org/W4406458238","doi":"https://doi.org/10.1109/bigdata62323.2024.10825731","title":"Benchmarking Human and Automated Prompting in the Segment Anything Model","display_name":"Benchmarking Human and Automated Prompting in the Segment Anything Model","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458238","doi":"https://doi.org/10.1109/bigdata62323.2024.10825731"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5069617607","display_name":"Jorge R. Quesada","orcid":"https://orcid.org/0000-0002-0438-0691"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jorge Quesada","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050378842","display_name":"Zoe Fowler","orcid":"https://orcid.org/0009-0008-7145-7266"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoe Fowler","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mohammad Alotaibi","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Alotaibi","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010958338","display_name":"Mohit Prabhushankar","orcid":"https://orcid.org/0000-0002-8743-7058"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Prabhushankar","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006145139","display_name":"Ghassan AlRegib","orcid":"https://orcid.org/0000-0001-6818-8001"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghassan AlRegib","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Centre for Signal and Info. Processing,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.74,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90703353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1625","last_page":"1634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9868999719619751,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8436793088912964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6489248871803284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3284202814102173},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.1337682008743286}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8436793088912964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489248871803284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3284202814102173},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1337682008743286},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W2044465660","https://openalex.org/W2049981393","https://openalex.org/W2083620785","https://openalex.org/W2130103520","https://openalex.org/W2963096510","https://openalex.org/W2963941635","https://openalex.org/W2963946669","https://openalex.org/W2997286550","https://openalex.org/W3032012374","https://openalex.org/W3195577433","https://openalex.org/W4214561053","https://openalex.org/W4283388932","https://openalex.org/W4368755247","https://openalex.org/W4383180696","https://openalex.org/W4383180710","https://openalex.org/W4389430914","https://openalex.org/W4390874575","https://openalex.org/W4391021462","https://openalex.org/W4391109864","https://openalex.org/W4392270593","https://openalex.org/W4401824963","https://openalex.org/W4402904060","https://openalex.org/W6631190155","https://openalex.org/W6770523219","https://openalex.org/W6778274454","https://openalex.org/W6800751262","https://openalex.org/W6839643428","https://openalex.org/W6846221585","https://openalex.org/W6852909635","https://openalex.org/W6853613540"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"The":[0],"remarkable":[1],"capabilities":[2],"of":[3,26,37,57,79,90,99,128,135,141,186],"the":[4,24,35,76,87,97,105,139,142,162,222,253],"Segment":[5],"Anything":[6],"Model":[7],"(SAM)":[8],"for":[9,155],"tackling":[10],"image":[11,73],"segmentation":[12,109,164],"tasks":[13,130],"in":[14,23],"an":[15,133],"intuitive":[16],"and":[17,124,150,179,228,256],"interactive":[18],"manner":[19],"has":[20,32],"sparked":[21],"interest":[22,31],"design":[25],"effective":[27,156,245],"visual":[28,62,83,120,157,246],"prompts.":[29,158],"Such":[30],"led":[33],"to":[34,69,137,210,243],"creation":[36],"automated":[38,61,82,148,177,203,229],"point":[39],"prompt":[40,106,247],"selection":[41],"strategies,":[42],"typically":[43],"motivated":[44],"from":[45,147],"a":[46,117,126,213],"feature":[47],"extraction":[48],"perspective.":[49],"However,":[50],"there":[51],"is":[52],"still":[53],"very":[54],"little":[55],"understanding":[56,140],"how":[58],"appropriate":[59],"these":[60,113],"prompting":[63,84,121,187],"strategies":[64,85,178],"are,":[65],"particularly":[66],"when":[67,201],"compared":[68],"humans,":[70],"across":[71],"diverse":[72],"domains.":[74],"Additionally,":[75,196],"performance":[77,188,200],"benefits":[78],"including":[80],"such":[81],"within":[86],"finetuning":[88,214],"process":[89],"SAM":[91],"also":[92,232],"remains":[93],"unexplored,":[94],"as":[95],"does":[96],"effect":[98],"interpretable":[100],"factors":[101,153],"like":[102],"distance":[103],"between":[104,225],"points":[107],"on":[108],"performance.":[110],"To":[111],"bridge":[112],"gaps,":[114],"we":[115,197],"leverage":[116],"recently":[118],"released":[119],"dataset,":[122],"PointPrompt,":[123],"introduce":[125],"number":[127],"benchmarking":[129],"that":[131,161,183,199],"provide":[132],"array":[134],"opportunities":[136],"improve":[138,244],"way":[143],"human":[144,226],"prompts":[145,227],"differ":[146],"ones":[149],"what":[151],"underlying":[152],"make":[154],"We":[159],"demonstrate":[160,198],"resulting":[163],"scores":[165,193],"obtained":[166],"by":[167,176,208],"humans":[168],"are":[169,184,258],"approximately":[170],"29%":[171],"higher":[172],"than":[173],"those":[174],"given":[175],"identify":[180],"potential":[181,234],"features":[182],"indicative":[185],"with":[189,252],"R<sup":[190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[192],"over":[194],"0.5.":[195],"using":[202],"methods":[204],"can":[205,240],"be":[206,241],"improved":[207],"up":[209],"68%":[211],"via":[212],"approach.":[215],"Overall,":[216],"our":[217],"experiments":[218],"not":[219],"only":[220],"showcase":[221],"existing":[223],"gap":[224,239],"methods,":[230],"but":[231],"highlight":[233],"avenues":[235],"through":[236],"which":[237],"this":[238],"leveraged":[242],"design.":[248],"Further":[249],"details":[250],"along":[251],"dataset":[254],"links":[255],"codes":[257],"available":[259],"at":[260],"https://github.com/olivesgatech/PointPrompt":[261]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}