{"id":"https://openalex.org/W4414360584","doi":"https://doi.org/10.24963/ijcai.2025/259","title":"Denoising Diffusion Models are Good General Gaze Feature Learners","display_name":"Denoising Diffusion Models are Good General Gaze Feature Learners","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360584","doi":"https://doi.org/10.24963/ijcai.2025/259"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/259","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5038901435","display_name":"Guanzhong Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guanzhong Zeng","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426857","display_name":"Jingjing Wang","orcid":"https://orcid.org/0000-0002-0657-8300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Wang","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030811167","display_name":"Pengwei Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengwei Yin","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025410111","display_name":"Zefu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zefu Xu","raw_affiliation_strings":["Hikvision Research Institute"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023686661","display_name":"Mingyang Zhou","orcid":"https://orcid.org/0000-0001-5996-3395"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Zhou","raw_affiliation_strings":["Shenzhen University"],"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038901435"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27031083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2323","last_page":"2331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9534000158309937,"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":0.9534000158309937,"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/T11184","display_name":"Neonatal and fetal brain pathology","score":0.9294000267982483,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9240999817848206,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7976999878883362},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7508999705314636},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7271000146865845},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5838000178337097},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3962000012397766},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3856000006198883}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8043000102043152},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7976999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508999705314636},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7508999705314636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7271000146865845},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5838000178337097},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5645999908447266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5461999773979187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/259","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Since":[0],"the":[1,31,100,104,109,144],"collection":[2],"of":[3,34],"labeled":[4],"gaze":[5,61,80,96,114,157],"data":[6,22],"is":[7],"laborious":[8],"and":[9,134,139],"time-consuming,":[10],"methods":[11],"which":[12,126],"can":[13,56],"learn":[14,113],"generalizable":[15],"features":[16,116],"by":[17,99],"leveraging":[18],"large-scale":[19],"available":[20],"unlabeled":[21],"are":[23,153],"desirable.":[24],"In":[25,49],"recent":[26],"years,":[27],"we":[28,52,70,85,119],"have":[29],"witnessed":[30],"tremendous":[32],"capabilities":[33],"diffusion":[35,77,89,110,151],"models":[36,78,152],"in":[37,45],"generating":[38],"images":[39],"as":[40,42,103,117,143],"well":[41],"their":[43],"potential":[44],"feature":[46,123,137,158],"representation":[47],"learning.":[48],"this":[50,68],"paper,":[51],"investigate":[53],"whether":[54],"they":[55],"acquire":[57],"discriminative":[58],"representations":[59],"for":[60,79],"estimation":[62],"via":[63],"generative":[64],"pre-training.":[65],"To":[66,107],"achieve":[67],"goal,":[69],"propose":[71,120],"a":[72,87,121],"self-supervised":[73],"learning":[74,124],"framework":[75],"with":[76,95],"estimation,":[81],"called":[82],"GazeDiff.":[83],"Specifically,":[84],"utilize":[86],"conditional":[88,145],"model":[90,111],"to":[91,112],"generate":[92],"target":[93],"image":[94,102],"direction":[97,136],"specified":[98],"reference":[101],"pre-training":[105],"task.":[106],"facilitate":[108],"related":[115],"condition,":[118],"disentangling":[122],"strategy,":[125],"first":[127],"learns":[128],"appearance":[129],"feature,":[130,133],"head":[131],"pose":[132],"eye":[135],"respectively,":[138],"then":[140],"combines":[141],"them":[142],"features.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"denoising":[150],"also":[154],"good":[155],"general":[156],"learners.":[159]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}