{"id":"https://openalex.org/W7164863004","doi":"https://doi.org/10.1145/3805622.3810610","title":"Empowering Vision Language Models for Training-Free Visual Search via Context-Aware Scanpath Simulation","display_name":"Empowering Vision Language Models for Training-Free Visual Search via Context-Aware Scanpath Simulation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164863004","doi":"https://doi.org/10.1145/3805622.3810610"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810610","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810610","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/10.1145/3805622.3810610","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100324819","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-0769-600X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8326-4980","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109298763","display_name":"Dan Wan","orcid":"https://orcid.org/0000-0002-8198-0754"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Wan","raw_affiliation_strings":["Renmin University of China, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-6310-710X","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.94105964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"206","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.988099992275238,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.988099992275238,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0010000000474974513,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/bottleneck","display_name":"Bottleneck","score":0.6054999828338623},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.6049000024795532},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/foveal","display_name":"Foveal","score":0.5339999794960022},{"id":"https://openalex.org/keywords/saccadic-masking","display_name":"Saccadic masking","score":0.4975000023841858},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4970000088214874},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4837000072002411},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4810999929904938},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.460099995136261},{"id":"https://openalex.org/keywords/gaze-contingency-paradigm","display_name":"Gaze-contingency paradigm","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757099986076355},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.6049000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5561000108718872},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C30181142","wikidata":"https://www.wikidata.org/wiki/Q865103","display_name":"Foveal","level":3,"score":0.5339999794960022},{"id":"https://openalex.org/C11054436","wikidata":"https://www.wikidata.org/wiki/Q7396580","display_name":"Saccadic masking","level":3,"score":0.4975000023841858},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.414900004863739},{"id":"https://openalex.org/C164280684","wikidata":"https://www.wikidata.org/wiki/Q5529040","display_name":"Gaze-contingency paradigm","level":4,"score":0.40799999237060547},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C153050134","wikidata":"https://www.wikidata.org/wiki/Q760256","display_name":"Eye movement","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810610","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810610","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:10.1145/3805622.3810610","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810610","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":[{"score":0.7577722668647766,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3000387804","https://openalex.org/W3022720704","https://openalex.org/W3154689434","https://openalex.org/W3176796859","https://openalex.org/W4386057737","https://openalex.org/W4391094120","https://openalex.org/W4394625686","https://openalex.org/W4402670262","https://openalex.org/W4402727606","https://openalex.org/W4402727815","https://openalex.org/W4402916414","https://openalex.org/W4407129516","https://openalex.org/W4412451763","https://openalex.org/W4412946581","https://openalex.org/W4413157193","https://openalex.org/W4415539028","https://openalex.org/W4415795415","https://openalex.org/W4415795981","https://openalex.org/W7133241532","https://openalex.org/W7160011496"],"related_works":[],"abstract_inverted_index":{"Current":[0],"Vision":[1],"Language":[2],"Models":[3],"(VLMs)":[4],"have":[5],"demonstrated":[6],"remarkable":[7],"proficiency":[8],"in":[9,166],"general":[10],"visual":[11,45,68,167],"understanding.":[12],"However,":[13],"they":[14],"encounter":[15],"a":[16,59,84,90,163,170],"critical":[17],"perception":[18],"bottleneck":[19],"when":[20],"applied":[21],"to":[22,42,99,115,147],"Training-free":[23],"Visual":[24],"Search,":[25],"particularly":[26],"for":[27],"fine-grained":[28],"or":[29],"small":[30],"objects.":[31],"Relying":[32],"on":[33,83,154],"static,":[34],"low-resolution":[35],"holistic":[36],"encoding,":[37],"standard":[38],"VLMs":[39,65],"often":[40],"fail":[41],"distinguish":[43],"actual":[44],"evidence":[46],"from":[47,78],"hallucinations":[48],"driven":[49],"by":[50,120],"language":[51],"priors.":[52],"To":[53],"address":[54],"this,":[55],"we":[56,88,132],"introduce":[57],"GazeSim,":[58],"novel":[60],"training-free":[61],"framework":[62],"that":[63,95,160],"transforms":[64],"into":[66],"active":[67],"agents":[69],"capable":[70],"of":[71,129],"mimicking":[72],"human":[73],"search":[74,105],"behaviors.":[75],"Drawing":[76],"inspiration":[77],"cognitive":[79],"processes,":[80],"GazeSim":[81,161],"operates":[82],"\"Look-Plan-Verify\"":[85],"paradigm.":[86],"First,":[87],"propose":[89],"Visual-Aligned":[91],"Context":[92],"Retrieval":[93],"mechanism":[94],"selects":[96],"layout-aware":[97],"demonstrations":[98],"implicitly":[100],"teach":[101],"the":[102,108,137,144,155],"model":[103,138],"scene-specific":[104],"strategies.":[106],"Second,":[107],"VLM":[109],"acts":[110],"as":[111,124],"an":[112],"agentic":[113],"planner":[114],"generate":[116],"dynamic":[117],"scanpaths":[118],"governed":[119],"biological":[121],"constraints,":[122],"such":[123],"saccadic":[125],"amplitude":[126],"and":[127,157],"inhibition":[128],"return.":[130],"Finally,":[131],"implement":[133],"Foveal":[134],"Verification,":[135],"where":[136],"scrutinizes":[139],"high-resolution":[140],"local":[141],"crops":[142],"along":[143],"simulated":[145],"trajectory":[146],"perform":[148],"coarse-to-fine":[149],"joint":[150],"reasoning.":[151],"Extensive":[152],"experiments":[153],"COCO-Search18":[156],"COCO-FreeView":[158],"demonstrate":[159],"establishes":[162],"new":[164],"state-of-the-art":[165],"search,":[168],"achieving":[169],"significant":[171],"accuracy":[172],"improvement":[173],"over":[174],"existing":[175],"baselines.":[176]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}