{"id":"https://openalex.org/W4416525316","doi":"https://doi.org/10.1109/iccv51701.2025.01943","title":"Visual Textualization for Image Prompted Object Detection","display_name":"Visual Textualization for Image Prompted Object Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416525316","doi":"https://doi.org/10.1109/iccv51701.2025.01943"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23785","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100716574","display_name":"Yongjian Wu","orcid":"https://orcid.org/0000-0002-5590-8396"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Wu","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715817","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0001-5031-0347"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092392020","display_name":"Jiya Saiyin","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiya Saiyin","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033792432","display_name":"Bingzheng Wei","orcid":"https://orcid.org/0000-0001-6979-0459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingzheng Wei","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100685723","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0002-6693-8494"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Xu","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.40891874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20900","last_page":"20910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8859000205993652,"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":0.8859000205993652,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03750000149011612,"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":0.027699999511241913,"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/pascal","display_name":"Pascal (unit)","score":0.7537000179290771},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7172999978065491},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47589999437332153},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4706000089645386},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46470001339912415},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4300000071525574},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785999774932861},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7172999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6870999932289124},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5358999967575073},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23785","pdf_url":"https://arxiv.org/pdf/2506.23785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.23785","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23785","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23785","pdf_url":"https://arxiv.org/pdf/2506.23785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335793","display_name":"Academic Excellence Foundation of BUAA for PHD Students","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"VisTex-OVLM,":[2],"a":[3,15,19,65],"novel":[4],"image":[5],"prompted":[6],"object":[7],"detection":[8],"method":[9,91],"that":[10,17,39,80],"introduces":[11],"visual":[12,21,71,74,78],"textualization":[13],"--":[14],"process":[16],"projects":[18],"few":[20],"exemplars":[22],"into":[23],"the":[24,93],"text":[25,85],"feature":[26],"space":[27],"to":[28,42,69],"enhance":[29],"Object-level":[30],"Vision-Language":[31],"Models'":[32],"(OVLMs)":[33],"capability":[34],"in":[35,105],"detecting":[36],"rare":[37],"categories":[38],"are":[40],"difficult":[41],"describe":[43],"textually":[44],"and":[45,64,123,132],"nearly":[46],"absent":[47],"from":[48,73],"their":[49,54],"pre-training":[50,121],"data,":[51],"while":[52,102],"preserving":[53],"pre-trained":[55],"object-text":[56],"alignment.":[57],"Specifically,":[58],"VisTex-OVLM":[59,108],"leverages":[60],"multi-scale":[61],"textualizing":[62],"blocks":[63],"multi-stage":[66],"fusion":[67],"strategy":[68],"integrate":[70],"information":[72],"exemplars,":[75],"generating":[76],"textualized":[77],"tokens":[79],"effectively":[81],"guide":[82],"OVLMs":[83],"alongside":[84],"prompts.":[86],"Unlike":[87],"previous":[88],"methods,":[89],"our":[90],"maintains":[92],"original":[94],"architecture":[95],"of":[96],"OVLM,":[97],"maintaining":[98],"its":[99],"generalization":[100],"capabilities":[101],"enhancing":[103],"performance":[104,111],"few-shot":[106,128],"settings.":[107],"demonstrates":[109],"superior":[110],"across":[112],"open-set":[113],"datasets":[114],"which":[115],"have":[116],"minimal":[117],"overlap":[118],"with":[119],"OVLM's":[120],"data":[122],"achieves":[124],"state-of-the-art":[125],"results":[126],"on":[127],"benchmarks":[129],"PASCAL":[130],"VOC":[131],"MSCOCO.":[133],"The":[134],"code":[135],"will":[136],"be":[137],"released":[138],"at":[139],"https://github.com/WitGotFlg/VisTex-OVLM.":[140]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}