{"id":"https://openalex.org/W4415538865","doi":"https://doi.org/10.1145/3746027.3758226","title":"AnaFig: A Human-Aligned Dataset for Scientific Figure Analysis","display_name":"AnaFig: A Human-Aligned Dataset for Scientific Figure Analysis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538865","doi":"https://doi.org/10.1145/3746027.3758226"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076464093","display_name":"Tan Yue","orcid":"https://orcid.org/0000-0002-5798-6304"},"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":"Tan Yue","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5798-6304","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032941440","display_name":"Xuzhao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuzhao Shi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5523-4563","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062187850","display_name":"Rui Mao","orcid":"https://orcid.org/0000-0002-1082-8755"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rui Mao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1082-8755","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048849627","display_name":"Zhiwen Song","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Song","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3688-5538","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088502323","display_name":"Zonghai Hu","orcid":"https://orcid.org/0000-0002-8362-6353"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonghai Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8362-6353","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037132097","display_name":"Dongyan Zhao","orcid":"https://orcid.org/0000-0002-0396-6703"},"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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyan Zhao","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China and State Key Laboratory of General Artificial Intelligence, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0396-6703","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China and State Key Laboratory of General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"12837","last_page":"12843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9936000108718872,"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/focus","display_name":"Focus (optics)","score":0.6031000018119812},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/scientific-reasoning","display_name":"Scientific reasoning","score":0.49390000104904175},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4717999994754791},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.4025999903678894},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4717999994754791},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2662999927997589}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/202549","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/202549","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2176950688","https://openalex.org/W3010343788","https://openalex.org/W3185585276","https://openalex.org/W3207024990","https://openalex.org/W4225143861","https://openalex.org/W4285095658","https://openalex.org/W4294982692","https://openalex.org/W4367674159","https://openalex.org/W4384207668"],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"Figure":[1],"Analysis":[2],"(SFA)":[3],"aims":[4],"to":[5,41,122,142],"derive":[6],"analytical":[7,128],"insights":[8],"from":[9,31,51],"figures":[10],"while":[11],"incorporating":[12],"background":[13],"instructions.":[14],"Unlike":[15],"conventional":[16],"tasks":[17],"such":[18],"as":[19],"figure":[20],"captioning":[21],"or":[22],"description":[23],"generation,":[24],"which":[25],"focus":[26],"on":[27],"extracting":[28],"surface-level":[29],"information":[30],"the":[32,64,109,149],"sole":[33],"visual":[34,52,60],"modality,":[35],"SFA":[36,80],"requires":[37],"an":[38,79],"intelligent":[39],"system":[40],"summarize":[42],"key":[43],"patterns,":[44],"infer":[45],"implications,":[46],"and":[47,53,71,127,146,153],"contextualize":[48],"scientific":[49,67,143,157],"findings":[50],"textual":[54],"inputs.":[55],"It":[56],"demands":[57],"not":[58],"only":[59],"recognition":[61],"but":[62],"also":[63],"integration":[65],"of":[66,111,115,151],"knowledge,":[68],"multimodal":[69,116,125],"understanding,":[70],"contextual":[72],"reasoning.":[73],"In":[74],"this":[75,139],"work,":[76],"we":[77],"introduce":[78],"dataset,":[81],"AnaFig,":[82],"comprising":[83],"2,000":[84],"high-quality":[85],"samples":[86,91],"across":[87],"56":[88],"domains.":[89],"All":[90],"are":[92],"evaluated":[93],"by":[94],"using":[95],"human-aligned":[96],"five-dimensional":[97],"scoring":[98],"criteria,":[99],"resulting":[100],"10,000":[101],"human-annotated":[102],"score":[103],"labels.":[104],"The":[105],"AnaFig":[106],"dataset":[107],"facilitates":[108],"assessment":[110],"three":[112],"critical":[113],"capabilities":[114],"large":[117],"language":[118],"models":[119],"(MLLMs):":[120],"adherence":[121],"complex":[123],"instructions,":[124],"perception,":[126],"summarization.":[129],"By":[130],"building":[131],"a":[132],"new":[133],"benchmark":[134],"with":[135],"widely":[136],"used":[137],"MLLMs,":[138],"study":[140],"contributes":[141],"knowledge":[144],"discovery":[145],"reasoning,":[147],"fostering":[148],"alignment":[150],"MLLMs":[152],"human":[154],"experts":[155],"in":[156],"analysis.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}