{"id":"https://openalex.org/W4417095194","doi":"https://doi.org/10.48550/arxiv.2511.20770","title":"Text-Guided Semantic Image Encoder","display_name":"Text-Guided Semantic Image Encoder","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W4417095194","doi":"https://doi.org/10.48550/arxiv.2511.20770"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.20770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.20770","pdf_url":"https://arxiv.org/pdf/2511.20770","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.20770","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019866898","display_name":"Raghuveer Thirukovalluru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thirukovalluru, Raghuveer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091822496","display_name":"Xiaochuang Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xiaochuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055033421","display_name":"Bhuwan Dhingra","orcid":"https://orcid.org/0000-0002-6874-9515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhingra, Bhuwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061347220","display_name":"Emily Dinan","orcid":"https://orcid.org/0000-0003-0624-6311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinan, Emily","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005764737","display_name":"Maha Elbayad","orcid":"https://orcid.org/0000-0002-8389-231X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elbayad, Maha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40560001134872437,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40560001134872437,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2092999964952469,"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":0.03689999878406525,"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/encoder","display_name":"Encoder","score":0.7656999826431274},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7513999938964844},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.597599983215332},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5824999809265137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4912000000476837},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4487000107765198}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7656999826431274},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7513999938964844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524999737739563},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.597599983215332},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.20770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.20770","pdf_url":"https://arxiv.org/pdf/2511.20770","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.2511.20770","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.20770","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.20770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.20770","pdf_url":"https://arxiv.org/pdf/2511.20770","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0,49],"encoders,":[1],"a":[2,17],"fundamental":[3],"component":[4],"of":[5],"vision-language":[6],"models":[7],"(VLMs),":[8],"are":[9],"typically":[10],"pretrained":[11],"independently":[12],"before":[13],"being":[14],"aligned":[15],"with":[16,64,88,127],"language":[18],"model.":[19],"This":[20],"standard":[21],"paradigm":[22],"results":[23],"in":[24,118],"encoders":[25],"that":[26,131,146],"process":[27],"images":[28],"agnostically,":[29],"without":[30],"regard":[31],"to":[32,92,138,150],"the":[33,46,58,82,136],"specific":[34],"downstream":[35],"task":[36],"or":[37],"text":[38,60],"query.":[39,61],"To":[40],"address":[41],"this":[42],"limitation,":[43],"we":[44],"propose":[45],"Text-Guided":[47],"Semantic":[48],"Encoder":[50],"(TIE),":[51],"which":[52],"generates":[53],"image":[54,114],"representations":[55],"conditioned":[56],"on":[57,75,95],"input":[59],"VLMs":[62,104],"equipped":[63],"TIE":[65,123,147],"outperform":[66],"their":[67],"conventional":[68],"counterparts":[69],"by":[70],"+1.5":[71],"and":[72,84,100,156],"+1.3":[73],"points":[74,94],"average":[76],"across":[77],"nine":[78],"image-to-text":[79],"benchmarks":[80],"at":[81],"1B":[83],"3B":[85],"scales,":[86],"respectively,":[87],"gains":[89],"reaching":[90],"up":[91],"6":[93],"tasks":[96],"such":[97],"as":[98,112],"DocVQA":[99],"InfoVQA.":[101],"Moreover,":[102],"TIE-based":[103],"attain":[105],"superior":[106],"performance":[107],"while":[108],"utilizing":[109],"only":[110],"half":[111],"many":[113],"tiles":[115],"(tokens),":[116],"resulting":[117],"notably":[119],"improved":[120],"inference":[121],"efficiency.":[122],"also":[124],"generalizes":[125],"well":[126],"generic":[128],"queries,":[129],"indicating":[130],"text-conditioned":[132],"training":[133],"effectively":[134],"optimizes":[135],"encoder":[137],"capture":[139],"key":[140],"visual":[141],"features.":[142],"Qualitative":[143],"analysis":[144],"confirms":[145],"consistently":[148],"attends":[149],"query-relevant":[151],"regions,":[152],"enhancing":[153],"both":[154],"interpretability":[155],"query-specific":[157],"grounding.":[158]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-28T00:00:00"}