{"id":"https://openalex.org/W4414937570","doi":"https://doi.org/10.48550/arxiv.2505.08819","title":"Thoughts on Objectives of Sparse and Hierarchical Masked Image Model","display_name":"Thoughts on Objectives of Sparse and Hierarchical Masked Image Model","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4414937570","doi":"https://doi.org/10.48550/arxiv.2505.08819"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.08819","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08819","pdf_url":"https://arxiv.org/pdf/2505.08819","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":"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/2505.08819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115833501","display_name":"A. Miyazaki","orcid":"https://orcid.org/0009-0004-3233-5080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miyazaki, Asahi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026921207","display_name":"Tsuyoshi Okita","orcid":"https://orcid.org/0000-0002-1286-5496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Okita, Tsuyoshi","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/T14254","display_name":"Digital Media and Visual Art","score":0.6633999943733215,"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"}},"topics":[{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.6633999943733215,"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/masking","display_name":"Masking (illustration)","score":0.7723000049591064},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7537999749183655},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3546999990940094}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7723000049591064},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7537999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6730999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6650000214576721},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.578000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.08819","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08819","pdf_url":"https://arxiv.org/pdf/2505.08819","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.08819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.08819","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.08819","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08819","pdf_url":"https://arxiv.org/pdf/2505.08819","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":"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":{"Masked":[0],"image":[1,55],"modeling":[2],"is":[3],"one":[4],"of":[5,10,49],"the":[6,13,40,47,50],"most":[7],"poplular":[8],"objectives":[9],"training.":[11],"Recently,":[12],"SparK":[14,35,43],"model":[15],"has":[16],"been":[17],"proposed":[18],"with":[19],"superior":[20],"performance":[21],"among":[22],"self-supervised":[23],"learning":[24],"models.":[25],"This":[26],"paper":[27],"proposes":[28],"a":[29],"new":[30],"mask":[31,51],"pattern":[32,52],"for":[33,54],"this":[34],"model,":[36],"proposing":[37],"it":[38],"as":[39],"Mesh":[41],"Mask-ed":[42],"model.":[44],"We":[45],"report":[46],"effect":[48],"used":[53],"masking":[56],"in":[57],"pre-training":[58],"on":[59],"performance.":[60]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}