{"id":"https://openalex.org/W4416214877","doi":"https://doi.org/10.1109/tmm.2025.3632641","title":"From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection","display_name":"From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214877","doi":"https://doi.org/10.1109/tmm.2025.3632641"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3632641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632641","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Qi Qin","orcid":"https://orcid.org/0000-0003-2294-4005"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Qin","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2294-4005","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091558139","display_name":"Runmin Cong","orcid":"https://orcid.org/0000-0003-0972-4008"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Cong","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-0972-4008","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078547821","display_name":"Gen Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093586","display_name":"Inovance (China)","ror":"https://ror.org/00gw0v185","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Zhan","raw_affiliation_strings":["ByteDance China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-8993-5316","affiliations":[{"raw_affiliation_string":"ByteDance China, Shenzhen, China","institution_ids":["https://openalex.org/I4210093586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101099254","display_name":"Yiting Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147763","display_name":"APIC (United States)","ror":"https://ror.org/055kw3s45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210147763"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiting Liao","raw_affiliation_strings":["ByteDance USA, Culver City, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance USA, Culver City, CA, USA","institution_ids":["https://openalex.org/I4210147763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["Lingnan University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"Lingnan University, Hong Kong","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5544,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7001625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"28","issue":null,"first_page":"1090","last_page":"1103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9962999820709229,"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"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9962999820709229,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.0017000000225380063,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.00019999999494757503,"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/object-detection","display_name":"Object detection","score":0.5472999811172485},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5351999998092651},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5347999930381775},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5144000053405762},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4934000074863434},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.483599990606308},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4318999946117401},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4287000000476837},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4219000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6919999718666077},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5472999811172485},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4934000074863434},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4359000027179718},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3632641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632641","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1914386590","display_name":null,"funder_award_id":"62471278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326189","display_name":"Taishan Scholar Project of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2076756823","https://openalex.org/W2110019070","https://openalex.org/W2130184867","https://openalex.org/W2135957164","https://openalex.org/W2138682569","https://openalex.org/W2470139095","https://openalex.org/W2514658199","https://openalex.org/W2547489168","https://openalex.org/W2740667773","https://openalex.org/W2798807298","https://openalex.org/W2798991696","https://openalex.org/W2799077596","https://openalex.org/W2799108379","https://openalex.org/W2884530474","https://openalex.org/W2894890793","https://openalex.org/W2895340898","https://openalex.org/W2938260698","https://openalex.org/W2939217524","https://openalex.org/W2955060956","https://openalex.org/W2963091558","https://openalex.org/W2963136160","https://openalex.org/W2963581854","https://openalex.org/W2963868681","https://openalex.org/W2964352379","https://openalex.org/W2965638232","https://openalex.org/W2984144959","https://openalex.org/W2986056979","https://openalex.org/W2986131415","https://openalex.org/W2990984982","https://openalex.org/W2997217064","https://openalex.org/W3034453930","https://openalex.org/W3035524453","https://openalex.org/W3096609285","https://openalex.org/W3097848036","https://openalex.org/W3099561715","https://openalex.org/W3138516171","https://openalex.org/W3165926952","https://openalex.org/W3173331776","https://openalex.org/W3175841511","https://openalex.org/W3180447501","https://openalex.org/W3202477427","https://openalex.org/W3204446219","https://openalex.org/W3204643350","https://openalex.org/W4214506192","https://openalex.org/W4214542306","https://openalex.org/W4221167637","https://openalex.org/W4224330024","https://openalex.org/W4226216113","https://openalex.org/W4294982611","https://openalex.org/W4304014270","https://openalex.org/W4312647976","https://openalex.org/W4312664986","https://openalex.org/W4313007081","https://openalex.org/W4362654014","https://openalex.org/W4385245566","https://openalex.org/W4386066371","https://openalex.org/W4388543960","https://openalex.org/W4390044151","https://openalex.org/W4390738771","https://openalex.org/W4399618322","https://openalex.org/W4406857013","https://openalex.org/W4408162342","https://openalex.org/W4413146091"],"related_works":[],"abstract_inverted_index":{"The":[0],"eye-tracking":[1],"video":[2,8,22,72],"saliency":[3,35],"prediction":[4],"(VSP)":[5],"task":[6,13],"and":[7,23,33,48,88,95,100,108,134,139,146,157,184],"salient":[9,73],"object":[10,159],"detection":[11,70],"(VSOD)":[12],"both":[14],"focus":[15],"on":[16,191,203],"the":[17,25,28,52,69,79,90,112,117,129,154,173],"most":[18,155],"attractive":[19],"objects":[20,74],"in":[21,27],"show":[24],"result":[26],"form":[29],"of":[30,56,71,131],"predictive":[31],"heatmaps":[32],"pixel-level":[34],"masks,":[36],"respectively.":[37],"In":[38,164],"practical":[39],"applications,":[40],"eye":[41],"tracker":[42],"annotations":[43],"are":[44],"more":[45],"readily":[46],"obtainable":[47],"align":[49],"closely":[50],"with":[51,144],"authentic":[53],"visual":[54],"patterns":[55],"human":[57],"eyes.":[58],"Therefore,":[59],"this":[60],"paper":[61],"aims":[62],"to":[63,67,85,105,151],"introduce":[64],"fixation":[65],"information":[66,91],"assist":[68],"under":[75,125,177],"weak":[76,126,178],"supervision.":[77],"On":[78,116],"one":[80],"hand,":[81,119],"we":[82,120],"ponder":[83],"how":[84],"better":[86],"explore":[87],"utilize":[89],"provided":[92],"by":[93,180],"fixation,":[94],"then":[96],"propose":[97],"a":[98],"Position":[99],"Semantic":[101],"Embedding":[102],"(PSE)":[103],"module":[104],"provide":[106],"location":[107],"semantic":[109,145],"guidance":[110],"during":[111],"feature":[113,123,132,135],"learning":[114,187],"process.":[115],"other":[118,201],"achieve":[121],"spatiotemporal":[122,162,174],"modeling":[124,175],"supervision":[127,179],"from":[128],"aspects":[130],"selection":[133],"contrast.":[136],"A":[137],"Semantics":[138],"Locality":[140],"Query":[141],"(SLQ)":[142],"Competitor":[143],"locality":[147],"constraints":[148],"is":[149],"designed":[150],"effectively":[152],"select":[153],"matching":[156],"accurate":[158],"query":[160],"for":[161],"modeling.":[163],"addition,":[165],"an":[166,182],"Intra-Inter":[167],"Mixed":[168],"Contrastive":[169],"(IIMC)":[170],"model":[171,199],"improves":[172],"capabilities":[176],"forming":[181],"intra-video":[183],"inter-video":[185],"contrastive":[186],"paradigm.":[188],"Experimental":[189],"results":[190],"five":[192],"popular":[193],"VSOD":[194],"benchmarks":[195],"indicate":[196],"that":[197],"our":[198],"outperforms":[200],"competitors":[202],"various":[204],"evaluation":[205],"metrics.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-11-14T00:00:00"}