{"id":"https://openalex.org/W4398230786","doi":"https://doi.org/10.48550/arxiv.2405.12757","title":"BIMM: Brain Inspired Masked Modeling for Video Representation Learning","display_name":"BIMM: Brain Inspired Masked Modeling for Video Representation Learning","publication_year":2024,"publication_date":"2024-05-21","ids":{"openalex":"https://openalex.org/W4398230786","doi":"https://doi.org/10.48550/arxiv.2405.12757"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.12757","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.12757","pdf_url":"https://arxiv.org/pdf/2405.12757","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.12757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087412143","display_name":"Zhifan Wan","orcid":"https://orcid.org/0009-0009-2742-3613","observed_orcids":["https://orcid.org/0009-0009-2742-3613"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wan, Zhifan","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China","University of Chinese Academy of Sciences , 19A Yuquan Rdn19A Yuquan Rd , Shijingshan District , 100049 , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , 19A Yuquan Rdn19A Yuquan Rd , Shijingshan District , 100049 , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662637","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0001-8219-5590","observed_orcids":["https://orcid.org/0000-0001-8219-5590"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jie","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078546128","display_name":"Changzhen Li","orcid":"https://orcid.org/0000-0002-8089-4838","observed_orcids":["https://orcid.org/0000-0002-8089-4838"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Changzhen","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050297728","display_name":"Shiguang Shan","orcid":"https://orcid.org/0000-0002-8348-392X","observed_orcids":["https://orcid.org/0000-0002-8348-392X"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan, Shiguang","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , No.6 Kexueyuan South Road Zhongguancun , Haidian District , 100190 , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.573199987411499,"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":0.573199987411499,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.21629999577999115,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09910000115633011,"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/video-representation-learning","display_name":"video representation learning","score":0.921999990940094},{"id":"https://openalex.org/keywords/ventral-stream","display_name":"ventral stream","score":0.8870000243186951},{"id":"https://openalex.org/keywords/dorsal-visual-pathway","display_name":"dorsal visual pathway","score":0.9990000128746033},{"id":"https://openalex.org/keywords/masked-modeling","display_name":"masked modeling","score":0.7689999938011169},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.8560000061988831},{"id":"https://openalex.org/keywords/progressive-reconstruction","display_name":"progressive reconstruction","score":0.44600000977516174},{"id":"https://openalex.org/keywords/visual-cortex","display_name":"visual cortex","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6780732274055481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5447652339935303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46915900707244873},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34983527660369873},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3375067114830017},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30676549673080444},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.074878990650177},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.12757","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.12757","pdf_url":"https://arxiv.org/pdf/2405.12757","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.2405.12757","doi":"https://doi.org/10.48550/arxiv.2405.12757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.12757","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.12757","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.12757","pdf_url":"https://arxiv.org/pdf/2405.12757","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398230786.pdf","grobid_xml":"https://content.openalex.org/works/W4398230786.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W2067108088","https://openalex.org/W2085372204","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"visual":[1,41,45,108,142],"pathway":[2,12],"of":[3,40,49,73,106,117],"human":[4,51],"brain":[5],"includes":[6],"two":[7],"sub-pathways,":[8],"ie,":[9],"the":[10,14,50,55,88,104,111,115,137,141,152,166],"ventral":[11,74],"and":[13,22,75,81,95,124],"dorsal":[15,76],"pathway,":[16],"which":[17,78],"focus":[18],"on":[19],"object":[20],"identification":[21],"dynamic":[23],"information":[24,46],"modeling,":[25],"respectively.":[26,84],"Both":[27,85],"pathways":[28],"comprise":[29],"multi-layer":[30],"structures,":[31],"with":[32,129],"each":[33,118],"layer":[34],"responsible":[35],"for":[36],"processing":[37,47],"different":[38,107],"aspects":[39],"information.":[42],"Inspired":[43,57],"by":[44],"mechanism":[48,139],"brain,":[52,112],"we":[53,113,144],"propose":[54,145],"Brain":[56],"Masked":[58],"Modeling":[59],"(BIMM)":[60],"framework,":[61],"aiming":[62],"to":[63,165],"learn":[64,79],"comprehensive":[65],"representations":[66],"from":[67,136],"videos.":[68],"Specifically,":[69],"our":[70],"approach":[71],"consists":[72],"branches,":[77],"image":[80],"video":[82],"representations,":[83],"branches":[86,153],"employ":[87],"Vision":[89],"Transformer":[90],"(ViT)":[91],"as":[92],"their":[93],"backbone":[94],"are":[96],"trained":[97],"using":[98],"masked":[99],"modeling":[100],"method.":[101],"To":[102],"achieve":[103],"goals":[105],"cortices":[109],"in":[110,140],"segment":[114],"encoder":[116],"branch":[119],"into":[120],"three":[121],"intermediate":[122],"blocks":[123],"reconstruct":[125],"progressive":[126],"prediction":[127],"targets":[128],"light":[130],"weight":[131],"decoders.":[132],"Furthermore,":[133],"drawing":[134],"inspiration":[135],"information-sharing":[138],"pathways,":[143],"a":[146],"partial":[147],"parameter":[148],"sharing":[149],"strategy":[150],"between":[151],"during":[154],"training.":[155],"Extensive":[156],"experiments":[157],"demonstrate":[158],"that":[159],"BIMM":[160],"achieves":[161],"superior":[162],"performance":[163],"compared":[164],"state-of-the-art":[167],"methods.":[168]},"counts_by_year":[],"updated_date":"2026-10-03T13:16:28.481748","created_date":"2025-10-10T00:00:00"}