{"id":"https://openalex.org/W4409263152","doi":"https://doi.org/10.1109/wacv61041.2025.00091","title":"Attention-Guided Masked Autoencoders for Learning Image Representations","display_name":"Attention-Guided Masked Autoencoders for Learning Image Representations","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4409263152","doi":"https://doi.org/10.1109/wacv61041.2025.00091"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61041.2025.00091","doi":"https://doi.org/10.1109/wacv61041.2025.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00091","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.15172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092772246","display_name":"Leon Sick","orcid":"https://orcid.org/0009-0004-6524-0715","observed_orcids":["https://orcid.org/0009-0004-6524-0715"]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leon Sick","raw_affiliation_strings":["Ulm University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulm University","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066189200","display_name":"Dominik Engel","orcid":"https://orcid.org/0000-0002-5766-7215","observed_orcids":["https://orcid.org/0000-0002-5766-7215"]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Engel","raw_affiliation_strings":["Ulm University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulm University","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088394147","display_name":"Pedro Hermosilla","orcid":"https://orcid.org/0000-0003-3586-4741","observed_orcids":["https://orcid.org/0000-0003-3586-4741"]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Pedro Hermosilla","raw_affiliation_strings":["TU Vienna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Vienna","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061059879","display_name":"Timo Ropinski","orcid":"https://orcid.org/0000-0002-7857-5512","observed_orcids":["https://orcid.org/0000-0002-7857-5512"]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Ropinski","raw_affiliation_strings":["Ulm University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulm University","institution_ids":["https://openalex.org/I196349391"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1672,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90559184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"836","last_page":"846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5288000106811523,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5288000106811523,"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":0.42289999127388,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.014100000262260437,"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/masked-autoencoder","display_name":"masked autoencoder","score":0.996999979019165},{"id":"https://openalex.org/keywords/image-representation-learning","display_name":"image representation learning","score":0.8130000233650208},{"id":"https://openalex.org/keywords/unsupervised-pretraining","display_name":"unsupervised pre-training","score":0.9900000095367432},{"id":"https://openalex.org/keywords/attention-maps","display_name":"attention maps","score":0.6859999895095825},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.6610000133514404},{"id":"https://openalex.org/keywords/linear-probing","display_name":"linear probing","score":0.7459999918937683},{"id":"https://openalex.org/keywords/background-robustness","display_name":"background robustness","score":0.9010000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409184575080872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.64244145154953},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.576328456401825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44252264499664307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3824222683906555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33716094493865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61041.2025.00091","doi":"https://doi.org/10.1109/wacv61041.2025.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00091","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.15172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15172","pdf_url":"https://arxiv.org/pdf/2402.15172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.15172","doi":"https://doi.org/10.48550/arxiv.2402.15172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.15172","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.15172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15172","pdf_url":"https://arxiv.org/pdf/2402.15172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409263152.pdf","grobid_xml":"https://content.openalex.org/works/W4409263152.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2121947440","https://openalex.org/W2138011018","https://openalex.org/W2148809531","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2626778328","https://openalex.org/W2737258237","https://openalex.org/W2765793020","https://openalex.org/W2795296309","https://openalex.org/W2798512429","https://openalex.org/W2962858109","https://openalex.org/W2963341956","https://openalex.org/W3005680577","https://openalex.org/W3030163527","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3036438747","https://openalex.org/W3093154590","https://openalex.org/W3119997354","https://openalex.org/W3135367836","https://openalex.org/W3136635488","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3170863103","https://openalex.org/W3182707920","https://openalex.org/W4226002507","https://openalex.org/W4294255647","https://openalex.org/W4308503280","https://openalex.org/W4312436160","https://openalex.org/W4312443924","https://openalex.org/W4312804044","https://openalex.org/W4312891165","https://openalex.org/W4313021454","https://openalex.org/W4321512591","https://openalex.org/W4386057726","https://openalex.org/W4386071576","https://openalex.org/W4386075705","https://openalex.org/W4386076428","https://openalex.org/W4386113253","https://openalex.org/W4390873186","https://openalex.org/W4390889749","https://openalex.org/W4393147573","https://openalex.org/W4402727452","https://openalex.org/W4402754274","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4281772236","https://openalex.org/W6929559289","https://openalex.org/W4390344735","https://openalex.org/W7172100011","https://openalex.org/W4388976122","https://openalex.org/W7075993590","https://openalex.org/W4281709991","https://openalex.org/W4389104669","https://openalex.org/W7211985544","https://openalex.org/W4391272976"],"abstract_inverted_index":{"Masked":[0],"autoencoders":[1],"(MAEs)":[2],"have":[3],"established":[4,86],"themselves":[5],"as":[6],"a":[7],"powerful":[8],"method":[9],"for":[10,13],"unsupervised":[11,47],"pre-training":[12],"computer":[14],"vision":[15],"tasks.":[16],"While":[17],"vanilla":[18,102],"MAEs":[19],"put":[20,66],"equal":[21],"emphasis":[22,68],"on":[23,69,113],"reconstructing":[24,70],"the":[25,29,35,56,62,76,85,101,118],"individual":[26],"parts":[27],"of":[28,55],"image,":[30],"we":[31,50,59],"propose":[32],"to":[33,65,78],"inform":[34],"reconstruction":[36],"process":[37],"through":[38],"an":[39,52],"attention-guided":[40],"loss":[41,63],"function.":[42],"By":[43],"leveraging":[44],"advances":[45],"in":[46,61],"object":[48],"discovery,":[49],"obtain":[51],"attention":[53],"map":[54],"scene":[57],"which":[58],"employ":[60],"function":[64],"increased":[67],"relevant":[71],"objects,":[72],"thus":[73],"effectively":[74],"incentivizing":[75],"model":[77],"learn":[79,96],"more":[80,123],"object-focused":[81],"representations":[82,99],"without":[83],"compromising":[84],"masking":[87],"strategy.":[88],"Our":[89],"evaluations":[90],"show":[91],"that":[92],"our":[93],"pre-trained":[94],"models":[95],"better":[97],"latent":[98],"than":[100],"MAE,":[103],"demonstrated":[104],"by":[105],"improved":[106],"linear":[107],"probing":[108],"and":[109],"k-NN":[110],"classification":[111],"results":[112],"several":[114],"benchmarks":[115],"while":[116],"at":[117],"same":[119],"time":[120],"making":[121],"ViTs":[122],"robust":[124],"against":[125],"varying":[126],"backgrounds.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-04-09T00:00:00"}