{"id":"https://openalex.org/W7169873366","doi":"https://doi.org/10.1145/3810987.3815538","title":"VIVID: Vision-and-Text Integrated Vectorization for Image Documents","display_name":"VIVID: Vision-and-Text Integrated Vectorization for Image Documents","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7169873366","doi":"https://doi.org/10.1145/3810987.3815538"},"language":null,"primary_location":{"id":"doi:10.1145/3810987.3815538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810987.3815538","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 7th International Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3810987.3815538","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141254139","display_name":"Zhixin Yuan","orcid":"https://orcid.org/0009-0007-0105-953X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Yuan","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0105-953X","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5236-7469","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"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":"36","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.7968999743461609},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5327000021934509},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5059000253677368},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4934999942779541},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.41830000281333923},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.39969998598098755},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39719998836517334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025000095367432},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.7968999743461609},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956000089645386},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5327000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.3490999937057495},{"id":"https://openalex.org/C59662460","wikidata":"https://www.wikidata.org/wiki/Q170130","display_name":"Vector graphics","level":3,"score":0.3488999903202057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.2824999988079071},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3810987.3815538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810987.3815538","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 7th International Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3810987.3815538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810987.3815538","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 7th International Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2023950391","https://openalex.org/W2085261163","https://openalex.org/W2117228865","https://openalex.org/W2133665775","https://openalex.org/W2139808046","https://openalex.org/W2194775991","https://openalex.org/W2966583823","https://openalex.org/W2997154779","https://openalex.org/W3107232127","https://openalex.org/W4286611322","https://openalex.org/W4308550530","https://openalex.org/W4312884055","https://openalex.org/W4382466406","https://openalex.org/W4386076124","https://openalex.org/W4403616351","https://openalex.org/W4404782964","https://openalex.org/W4413147425"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"VIVID,":[2],"an":[3,40],"end-to-end":[4],"solution":[5],"for":[6],"converting":[7],"text-containing":[8],"images":[9],"to":[10,51,58,91],"Scalable":[11],"Vector":[12],"Graphics":[13],"(SVG).":[14],"Unlike":[15],"prior":[16],"work,":[17],"VIVID":[18,100],"explicitly":[19],"targets":[20],"the":[21,36,44,60,93],"dual":[22],"challenges":[23],"of":[24],"visual":[25],"fidelity":[26],"and":[27,47,67,76,111],"textual-semantic":[28],"preservation":[29],"by":[30,48],"injecting":[31],"OCR":[32],"results":[33,97],"extracted":[34],"from":[35],"input":[37],"image":[38],"as":[39],"additional":[41],"condition":[42],"into":[43],"SVG":[45],"generator,":[46],"using":[49],"LoRA":[50],"efficiently":[52],"fine-tune":[53],"a":[54,78],"Qwen3-VL":[55],"family":[56],"model":[57],"learn":[59],"pixel-to-SVG":[61],"mapping.":[62],"To":[63],"improve":[64],"generation":[65],"stability":[66],"renderability,":[68],"we":[69],"produce":[70],"multiple":[71],"candidates":[72],"via":[73],"multi-temperature":[74],"sampling":[75],"employ":[77],"pairwise-trained":[79],"learnable":[80],"reranker":[81],"that":[82,99],"learns":[83],"relative":[84],"preferences":[85],"on":[86],"automatically":[87],"constructed":[88],"candidate":[89],"pairs":[90],"select":[92],"final":[94],"output.":[95],"Empirical":[96],"show":[98],"yields":[101],"superior":[102],"performance":[103],"over":[104],"existing":[105],"methods":[106],"in":[107],"preserving":[108],"textual":[109],"content":[110],"layout":[112],"while":[113],"producing":[114],"consistent,":[115],"renderable":[116],"SVGs.":[117]},"counts_by_year":[],"updated_date":"2026-07-22T06:00:27.337203","created_date":"2026-07-22T00:00:00"}