{"id":"https://openalex.org/W4408352141","doi":"https://doi.org/10.1109/icassp49660.2025.10889887","title":"Keypoint Aware Masked Image Modelling","display_name":"Keypoint Aware Masked Image Modelling","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352141","doi":"https://doi.org/10.1109/icassp49660.2025.10889887"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113194940","display_name":"Madhava Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhava Krishna","raw_affiliation_strings":["IIIT,Department of CSE,Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Department of CSE,Delhi,India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037246207","display_name":"A. Subramanyam","orcid":"https://orcid.org/0009-0000-1951-3138"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A. V. Subramanyam","raw_affiliation_strings":["IIIT,Department of ECE,Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Department of ECE,Delhi,India","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":1.2829,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77003293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9563000202178955,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9563000202178955,"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/computer-science","display_name":"Computer science","score":0.6498540639877319},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5045310258865356},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49294590950012207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4553627371788025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498540639877319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5045310258865356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49294590950012207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553627371788025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1532362218","https://openalex.org/W2025768430","https://openalex.org/W2108598243","https://openalex.org/W2117228865","https://openalex.org/W2124386111","https://openalex.org/W2161969291","https://openalex.org/W2797977484","https://openalex.org/W2963420272","https://openalex.org/W2992308087","https://openalex.org/W3035524453","https://openalex.org/W3138516171","https://openalex.org/W3202897123","https://openalex.org/W4307823382","https://openalex.org/W4312312750","https://openalex.org/W4312349930","https://openalex.org/W4312804044","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W4393147573","https://openalex.org/W6679792166","https://openalex.org/W6682751323","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6796761347","https://openalex.org/W6800217721","https://openalex.org/W6804160461","https://openalex.org/W6851800889","https://openalex.org/W6852830873"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"SimMIM":[0],"is":[1,148],"a":[2,82,128],"widely":[3],"used":[4,29],"method":[5],"for":[6,30,85,117],"pretraining":[7,119],"vision":[8],"transformers":[9],"using":[10,131],"masked":[11],"image":[12],"modeling.":[13],"However,":[14],"despite":[15],"its":[16],"success":[17],"in":[18],"fine-tuning":[19],"performance,":[20],"it":[21],"has":[22],"been":[23],"shown":[24],"to":[25,67,74,139],"perform":[26],"sub-optimally":[27],"when":[28,76],"linear":[31,62,114],"probing.":[32],"We":[33,96,121],"propose":[34],"an":[35],"efficient":[36],"patch-wise":[37,111],"weighting":[38,112],"derived":[39],"from":[40,65,72],"keypoint":[41,103],"features":[42],"which":[43],"captures":[44],"the":[45,60,86,93,124],"local":[46],"information":[47],"and":[48,69,105,108,133],"provides":[49],"better":[50],"context":[51],"during":[52],"SimMIM\u2019s":[53],"reconstruction":[54],"phase.":[55],"Our":[56,146],"method,":[57],"KAMIM,":[58],"improves":[59],"top-1":[61],"probing":[63,115],"accuracy":[64,71],"16.12%":[66],"33.97%,":[68],"finetuning":[70],"76.78%":[73],"77.3%":[75],"tested":[77],"on":[78,100],"ImageNet-1K":[79],"dataset":[80],"with":[81,142],"ViT-B":[83,129],"trained":[84,130],"same":[87,94],"number":[88],"of":[89,127],"epochs":[90],"while":[91],"taking":[92],"wall-clock-time.":[95],"conduct":[97],"extensive":[98],"testing":[99],"different":[101],"datasets,":[102],"extractors,":[104],"model":[106],"architectures":[107],"observe":[109,134],"that":[110,135],"augments":[113],"performance":[116],"larger":[118],"datasets.":[120],"also":[122],"analyze":[123],"learned":[125],"representations":[126],"KAMIM":[132],"they":[136],"behave":[137],"similar":[138],"contrastive":[140],"learning":[141],"longer":[143],"attention":[144],"distances.":[145],"code":[147],"available":[149],"at":[150],"https://github.com/madhava20217/KAMIM.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}