{"id":"https://openalex.org/W7164858888","doi":"https://doi.org/10.1145/3805622.3810886","title":"SIGaze: Toward Pixel-Level Single-Instance Gaze Object Prediction","display_name":"SIGaze: Toward Pixel-Level Single-Instance Gaze Object Prediction","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164858888","doi":"https://doi.org/10.1145/3805622.3810886"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810886","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810886","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138663644","display_name":"Dongxing Duan","orcid":"https://orcid.org/0009-0008-2431-5580"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongxing Duan","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-2431-5580","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133613900","display_name":"Xu Liu","orcid":"https://orcid.org/0009-0003-3149-1615"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-3149-1615","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028154645","display_name":"Jingyuan Xu","orcid":"https://orcid.org/0000-0002-4462-315X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Xu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-4462-315X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754771","display_name":"Ruijie Liu","orcid":"https://orcid.org/0000-0001-5929-9586"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijie Liu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0002-0371-5557","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]}],"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":0.94978533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1523","last_page":"1532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9715999960899353,"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":0.9715999960899353,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.019700000062584877,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0007999999797903001,"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":0.8040000200271606},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5350000262260437},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5044999718666077},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3962000012397766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.3643999993801117}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8040000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7811999917030334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6204000115394592},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810886","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810886","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5165861908","display_name":null,"funder_award_id":"2024YFB3311600","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5212438387","display_name":null,"funder_award_id":"2408085J040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5633884624","display_name":null,"funder_award_id":"202423k09020001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5819124452","display_name":null,"funder_award_id":"JZ2024AHST0337\uff0cJZ2025HGQA0139\uff0cJZ2025HGTA0160\uff0c","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7882806471","display_name":null,"funder_award_id":"62272144\uff0c62501224","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2605289374","https://openalex.org/W2756252215","https://openalex.org/W2776312359","https://openalex.org/W2883284130","https://openalex.org/W2942368658","https://openalex.org/W2963299996","https://openalex.org/W2981311477","https://openalex.org/W2982770724","https://openalex.org/W2989604896","https://openalex.org/W2993182889","https://openalex.org/W3012573144","https://openalex.org/W3035735638","https://openalex.org/W3113929572","https://openalex.org/W3119381934","https://openalex.org/W3154013571","https://openalex.org/W3174359952","https://openalex.org/W3188642398","https://openalex.org/W4210800317","https://openalex.org/W4280492519","https://openalex.org/W4285116117","https://openalex.org/W4292793996","https://openalex.org/W4293253477","https://openalex.org/W4294286150","https://openalex.org/W4312510569","https://openalex.org/W4312567381","https://openalex.org/W4312815172","https://openalex.org/W4313061846","https://openalex.org/W4319300857","https://openalex.org/W4322706693","https://openalex.org/W4386071535","https://openalex.org/W4387010030","https://openalex.org/W4387446636","https://openalex.org/W4390872917","https://openalex.org/W4390874396","https://openalex.org/W4390874575","https://openalex.org/W4393147659","https://openalex.org/W4402715878","https://openalex.org/W4404600626","https://openalex.org/W4410037864","https://openalex.org/W4413147571"],"related_works":[],"abstract_inverted_index":{"Gaze":[0,59],"object":[1,8,60,196],"prediction":[2,61,140,197],"aims":[3],"to":[4,38,157],"accurately":[5],"predict":[6],"the":[7,25,46,75,86,97,112,153,168,172,181,193],"that":[9,185],"humans":[10],"are":[11],"gazing":[12],"at":[13],"in":[14,144,192],"a":[15,21,53,147],"scene.":[16],"Existing":[17],"methods":[18,191],"often":[19],"adopt":[20],"two-stage":[22],"pipeline,":[23],"matching":[24],"target":[26],"from":[27],"candidate":[28],"instances":[29],"via":[30,120],"gaze":[31,129,195],"heatmaps,":[32],"which":[33,110,136],"can":[34],"easily":[35],"fail":[36],"due":[37],"uneven":[39],"energy":[40],"distribution":[41],"or":[42],"spatial":[43],"offset":[44],"of":[45,88],"heatmaps.":[47],"To":[48,95],"address":[49,96],"this,":[50],"we":[51,64],"explore":[52],"direct":[54],"end-to-end":[55],"framework":[56],"for":[57],"Single-Instance":[58],"(SIGaze).":[62],"However,":[63],"find":[65],"this":[66],"is":[67],"not":[68],"easy,":[69],"with":[70,128],"two":[71,102],"main":[72],"challenges:":[73],"1)":[74],"weak":[76],"correlation":[77,113],"between":[78,114],"head":[79,115],"cues":[80],"and":[81,92,117,141,161,174,177],"global":[82],"scene":[83,118],"cues,":[84],"2)":[85],"difficulty":[87],"jointly":[89],"optimizing":[90,152],"segmentation":[91,139],"classification":[93],"objectives.":[94],"above":[98],"challenges,":[99],"SIGaze":[100],"contains":[101],"key":[103],"modules:":[104],"(1)":[105],"Head-Conditioned":[106],"Scene":[107],"Interactive":[108],"module,":[109,135],"captures":[111],"position":[116],"semantics":[119],"self-attention":[121],"mechanism,":[122],"effectively":[123],"focusing":[124],"on":[125,180],"regions":[126],"consistent":[127],"intent.":[130],"(2)":[131],"Cross-Interactive":[132],"Dual":[133],"Decoder":[134],"performs":[137],"instance-level":[138],"category":[142],"recognition":[143],"parallel":[145],"within":[146],"shared":[148],"feature":[149],"space,":[150],"better":[151],"segmentation-classification":[154],"joint":[155],"objective":[156],"achieve":[158],"semantically":[159],"clear":[160],"geometrically":[162],"precise":[163],"single-instance":[164,194],"prediction.":[165],"We":[166],"evaluate":[167],"proposed":[169],"method":[170,187],"under":[171],"wUoC":[173],"mSoC":[175],"metrics,":[176],"extensive":[178],"experiments":[179],"GOO":[182],"dataset":[183],"demonstrate":[184],"our":[186],"significantly":[188],"outperforms":[189],"existing":[190],"task.":[198]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}