{"id":"https://openalex.org/W4413278585","doi":"https://doi.org/10.1109/icip55913.2025.11084645","title":"Exploring The Potential of Vision-Language Models for Pure-Image and Text-Guided-Image Saliency Prediction","display_name":"Exploring The Potential of Vision-Language Models for Pure-Image and Text-Guided-Image Saliency Prediction","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413278585","doi":"https://doi.org/10.1109/icip55913.2025.11084645"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046117810","display_name":"Yuxin Zhu","orcid":"https://orcid.org/0009-0008-6904-1165"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015291775","display_name":"Huiyu Duan","orcid":"https://orcid.org/0000-0002-6519-4067"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004453915","display_name":"Patrick Le Callet","orcid":"https://orcid.org/0000-0002-2143-7063"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Le Callet","raw_affiliation_strings":["Nantes Université, Ecole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nantes Université, Ecole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France","institution_ids":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I4210117005","https://openalex.org/I97188460"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1569,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79176358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1780","last_page":"1785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9934999942779541,"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":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.6806238889694214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6729958653450012},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6691828370094299},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5932466387748718},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39600202441215515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6806238889694214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6729958653450012},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6691828370094299},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5932466387748718},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39600202441215515}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip55913.2025.11084645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05579402v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05579402","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP), Sep 2025, Anchorage, France. pp.1780-1785, ⟨10.1109/ICIP55913.2025.11084645⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1996031228","https://openalex.org/W2041719651","https://openalex.org/W2108825342","https://openalex.org/W2133589685","https://openalex.org/W2135957164","https://openalex.org/W2152233525","https://openalex.org/W2212216676","https://openalex.org/W2558906385","https://openalex.org/W2963828885","https://openalex.org/W3005401190","https://openalex.org/W3034429256","https://openalex.org/W4224281996","https://openalex.org/W4384947975","https://openalex.org/W4386071707","https://openalex.org/W4386076080","https://openalex.org/W4389328725","https://openalex.org/W4390873312","https://openalex.org/W4402742408"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,26],"introduce":[1],"VLSal,":[2],"a":[3,48,59],"saliency":[4,17,61,66,108],"prediction":[5,18],"framework":[6],"that":[7,98],"leverages":[8],"Vision-Language":[9],"Models":[10],"(VLMs)":[11],"to":[12,63],"unify":[13],"pure-image":[14,105],"and":[15,20,34,95,106],"text-guided-image":[16,107],"tasks":[19],"achieve":[21],"high":[22],"performance":[23],"in":[24,103],"both.":[25],"extract":[27],"visual":[28,32,38],"features":[29,40,54],"from":[30,41],"the":[31,36,42,71],"encoder":[33],"retrieve":[35],"corresponding":[37],"token":[39],"language":[43],"decoder,":[44],"which":[45],"serves":[46],"as":[47],"natural":[49],"feature":[50],"fusion":[51],"mechanism.":[52],"These":[53],"are":[55],"then":[56],"processed":[57],"through":[58],"U-Net-based":[60],"decoder":[62],"generate":[64],"accurate":[65],"maps.":[67],"To":[68],"efficiently":[69],"adapt":[70],"large-scale":[72],"pretrained":[73],"model,":[74],"we":[75],"apply":[76],"Low-Rank":[77],"Adaptation":[78],"(LoRA)":[79],"finetuning,":[80],"reducing":[81],"computational":[82],"costs":[83],"while":[84],"preserving":[85],"performance.":[86],"Extensive":[87],"experiments":[88],"on":[89],"benchmark":[90],"datasets,":[91],"including":[92],"SALICON,":[93],"MIT1003,":[94],"TIS,":[96],"demonstrate":[97],"VLSal":[99],"outperforms":[100],"existing":[101],"methods":[102],"both":[104],"prediction.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}