{"id":"https://openalex.org/W7135108673","doi":"https://doi.org/10.48550/arxiv.2603.10495","title":"IMTBench: A Multi-Scenario Cross-Modal Collaborative Evaluation Benchmark for In-Image Machine Translation","display_name":"IMTBench: A Multi-Scenario Cross-Modal Collaborative Evaluation Benchmark for In-Image Machine Translation","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135108673","doi":"https://doi.org/10.48550/arxiv.2603.10495"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.10495","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002479762","display_name":"Jiahao Lyu","orcid":"https://orcid.org/0000-0001-6788-3942"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lyu, Jiahao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128883422","display_name":"Pei Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Pei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128810409","display_name":"Zhenhang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhenhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128871288","display_name":"Weichao Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Weichao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126149960","display_name":"Shaojie Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shaojie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128825054","display_name":"Jiahui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiahui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128847972","display_name":"Can Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Can","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128892442","display_name":"Yu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128902700","display_name":"Zhenbo Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Zhenbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128826972","display_name":"Jian Luan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luan, Jian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5002479762"],"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":0.9345999956130981,"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":0.9345999956130981,"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":0.015200000256299973,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7813000082969666},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.730400025844574},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6327000260353088},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5582000017166138},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.4302999973297119}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7813000082969666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809000015258789},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.730400025844574},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608000159263611},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5270000100135803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4625000059604645},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.4302999973297119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"In-Image":[1],"Machine":[2,66],"Translation":[3,67],"(IIMT)":[4],"aims":[5],"to":[6,37,166],"convert":[7],"text":[8,55,108,115,157],"embedded":[9],"within":[10],"an":[11],"image":[12,75,95,156],"into":[13],"a":[14,70,98,163],"target":[15],"language":[16],"while":[17,41],"preserving":[18],"the":[19,106,111,114,118],"original":[20],"visual":[21],"context,":[22],"layout,":[23],"and":[24,34,49,56,82,97,113,127,130,135,142,148],"rendering":[25],"style.":[26],"However,":[27],"existing":[28],"IIMT":[29],"benchmarks":[30],"are":[31],"largely":[32],"synthetic":[33],"thus":[35],"fail":[36],"reflect":[38],"real-world":[39],"complexity,":[40],"current":[42],"evaluation":[43],"protocols":[44],"focus":[45],"on":[46,145],"single-modality":[47],"metrics":[48],"overlook":[50],"cross-modal":[51,99],"faithfulness":[52],"between":[53,105],"rendered":[54,116],"model":[57,112],"outputs.":[58],"To":[59],"address":[60],"these":[61],"shortcomings,":[62],"we":[63],"present":[64],"In-image":[65],"Benchmark":[68],"(IMTBench),":[69],"new":[71],"benchmark":[72,122,165],"of":[73],"2,500":[74],"translation":[76,90],"samples":[77],"covering":[78],"four":[79],"practical":[80],"scenarios":[81,141],"nine":[83],"languages.":[84],"IMTBench":[85,161],"supports":[86],"multi-aspect":[87],"evaluation,":[88],"including":[89],"quality,":[91,96],"background":[92],"preservation,":[93],"overall":[94],"alignment":[100],"score":[101],"that":[102],"measures":[103],"consistency":[104],"translated":[107,119],"produced":[109],"by":[110],"in":[117,169],"image.":[120],"We":[121,159],"strong":[123],"commercial":[124],"cascade":[125],"systems,":[126],"both":[128],"closed-":[129],"open-source":[131],"unified":[132],"multi-modal":[133],"models,":[134],"observe":[136],"large":[137],"performance":[138],"gaps":[139],"across":[140],"languages,":[143,150],"especially":[144],"natural":[146],"scenes":[147],"resource-limited":[149],"highlighting":[151],"substantial":[152],"headroom":[153],"for":[154],"end-to-end":[155],"translation.":[158],"hope":[160],"establishes":[162],"standardized":[164],"accelerate":[167],"progress":[168],"this":[170],"emerging":[171],"task.":[172]},"counts_by_year":[],"updated_date":"2026-04-03T16:38:21.277918","created_date":"2026-03-13T00:00:00"}