{"id":"https://openalex.org/W4406301791","doi":"https://doi.org/10.48550/arxiv.2408.01044","title":"Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model","display_name":"Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4406301791","doi":"https://doi.org/10.48550/arxiv.2408.01044"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.01044","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01044","pdf_url":"https://arxiv.org/pdf/2408.01044","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.01044","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jin, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jin, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116592761","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0003-1520-9360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659469","display_name":"Yan Shi","orcid":"https://orcid.org/0000-0002-6123-9870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842676","display_name":"Bin Fan","orcid":"https://orcid.org/0000-0002-8028-0166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Bin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043220498","display_name":"Binglu Wang","orcid":"https://orcid.org/0000-0002-9266-4685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Binglu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9510999917984009,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9337000250816345,"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/gaze","display_name":"Gaze","score":0.8037290573120117},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7390604019165039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6619977951049805},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6392855644226074},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6280401349067688},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.61041259765625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5810426473617554},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5062910318374634},{"id":"https://openalex.org/keywords/object-based","display_name":"Object based","score":0.4332055151462555},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.15629595518112183}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8037290573120117},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7390604019165039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6619977951049805},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6392855644226074},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6280401349067688},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.61041259765625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5810426473617554},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5062910318374634},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.4332055151462555},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.15629595518112183},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.01044","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01044","pdf_url":"https://arxiv.org/pdf/2408.01044","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.01044","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.01044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.01044","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01044","pdf_url":"https://arxiv.org/pdf/2408.01044","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W3014378845","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W4240909707"],"abstract_inverted_index":{"Gaze":[0],"object":[1,13,28,61,90,103,125,136],"prediction":[2,79,126],"(GOP)":[3],"aims":[4],"to":[5,25,101,127,133,161,169,187,213],"predict":[6,188],"the":[7,12,27,97,102,114,171,178,204,238,257],"category":[8],"and":[9,138,175,200,253],"location":[10,199],"of":[11,80,203,259],"that":[14,29,113,141,150],"a":[15,30,41,86,208,243],"human":[16,106],"is":[17,32],"looking":[18,33],"at.":[19],"Previous":[20],"methods":[21,149],"utilized":[22],"box-level":[23],"supervision":[24,116],"identify":[26],"person":[31],"at,":[34],"but":[35],"struggled":[36],"with":[37,233],"semantic":[38,129],"ambiguity,":[39],"ie,":[40],"single":[42],"box":[43,64],"may":[44,196],"contain":[45],"several":[46],"items":[47],"since":[48],"objects":[49],"are":[50],"close":[51],"together.":[52],"The":[53],"Vision":[54],"foundation":[55],"model":[56],"(VFM)":[57],"has":[58],"improved":[59],"in":[60,177,192,237],"segmentation":[62,91,139,239],"using":[63],"prompts,":[65],"which":[66,94,195],"can":[67,120],"reduce":[68],"confusion":[69],"by":[70,105,118,231],"more":[71,87],"precisely":[72],"locating":[73],"objects,":[74],"offering":[75],"advantages":[76],"for":[77,246],"fine-grained":[78],"gaze":[81,89,107,124,135,189,210,216,244],"objects.":[82],"This":[83,131],"paper":[84],"presents":[85],"challenging":[88],"(GOS)":[92],"task,":[93],"involves":[95],"inferring":[96],"pixel-level":[98,115,144],"mask":[99],"corresponding":[100],"captured":[104],"behavior.":[108],"In":[109],"particular,":[110],"we":[111,159,206],"propose":[112,160],"provided":[117],"VFM":[119],"be":[121],"integrated":[122],"into":[123],"mitigate":[128],"ambiguity.":[130],"leads":[132],"our":[134,260],"detection":[137],"framework":[140],"enables":[142],"accurate":[143],"predictions.":[145],"Different":[146],"from":[147,166],"previous":[148],"require":[151],"additional":[152],"head":[153,157,164],"input":[154],"or":[155],"ignore":[156],"features,":[158],"automatically":[162],"obtain":[163],"features":[165,168,186,236],"scene":[167],"ensure":[170],"model's":[172],"inference":[173],"efficiency":[174],"flexibility":[176],"real":[179],"world.":[180],"Moreover,":[181],"rather":[182],"than":[183],"directly":[184],"fuse":[185],"heatmap":[190,245],"as":[191],"existing":[193],"methods,":[194],"overlook":[197],"spatial":[198,225],"subtle":[201],"details":[202],"object,":[205],"develop":[207],"space-to-object":[209],"regression":[211],"method":[212],"facilitate":[214],"human-object":[215,224],"interaction.":[217],"Specifically,":[218],"it":[219],"first":[220],"constructs":[221],"an":[222],"initial":[223],"connection,":[226],"then":[227],"refines":[228],"this":[229],"connection":[230],"interacting":[232],"semantically":[234],"clear":[235],"branch,":[240],"ultimately":[241],"predicting":[242],"precise":[247],"localization.":[248],"Extensive":[249],"experiments":[250],"on":[251],"GOO-Synth":[252],"GOO-Real":[254],"datasets":[255],"demonstrate":[256],"effectiveness":[258],"method.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-01-13T00:00:00"}