{"id":"https://openalex.org/W7172012964","doi":"https://doi.org/10.1145/3774521.3774566","title":"Towards Structured Multimodal Understanding: Scientific Diagram Captioning with Modern VLMs","display_name":"Towards Structured Multimodal Understanding: Scientific Diagram Captioning with Modern VLMs","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7172012964","doi":"https://doi.org/10.1145/3774521.3774566"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774566","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 Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774566","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079311910","display_name":"Deepika Kamboj","orcid":"https://orcid.org/0000-0002-6740-3029"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]},{"id":"https://openalex.org/I4724304","display_name":"Jodhpur National University","ror":"https://ror.org/03rm49h74","country_code":"IN","type":"education","lineage":["https://openalex.org/I4724304"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepika Kamboj","raw_affiliation_strings":["Computer Science &amp; Engineering, IIT Jodhpur, Jodhpur, Rajasthan, India and School of Computer Science, UPES, dehradun, Uttarakhand, India"],"raw_orcid":"https://orcid.org/0000-0002-2576-8943","affiliations":[{"raw_affiliation_string":"Computer Science &amp; Engineering, IIT Jodhpur, Jodhpur, Rajasthan, India and School of Computer Science, UPES, dehradun, Uttarakhand, India","institution_ids":["https://openalex.org/I154549908","https://openalex.org/I4724304"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025684791","display_name":"Gaurav Harit","orcid":"https://orcid.org/0000-0001-7943-0123"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gaurav Harit","raw_affiliation_strings":["Computer Science &amp; Engineering, IIT Jodhpur, Jodhpur, Rajasthan, India"],"raw_orcid":"https://orcid.org/0000-0001-7943-0123","affiliations":[{"raw_affiliation_string":"Computer Science &amp; Engineering, IIT Jodhpur, Jodhpur, Rajasthan, India","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6157000064849854},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.45969998836517334},{"id":"https://openalex.org/keywords/state-diagram","display_name":"State diagram","score":0.30250000953674316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2921000123023987},{"id":"https://openalex.org/keywords/sequence-diagram","display_name":"Sequence diagram","score":0.26600000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518999934196472},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6157000064849854},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36579999327659607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C16671368","wikidata":"https://www.wikidata.org/wiki/Q230885","display_name":"State diagram","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C153185123","wikidata":"https://www.wikidata.org/wiki/Q1391624","display_name":"Sequence diagram","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774566","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 Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774566","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 Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2101105183","https://openalex.org/W2307512708","https://openalex.org/W2886641317","https://openalex.org/W2997154779","https://openalex.org/W3009518609","https://openalex.org/W3090449556","https://openalex.org/W3120043490","https://openalex.org/W3206987730","https://openalex.org/W4285255856","https://openalex.org/W4304013646","https://openalex.org/W4366352717"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}
