{"id":"https://openalex.org/W4376988750","doi":"https://doi.org/10.48550/arxiv.2305.09156","title":"Modelling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network","display_name":"Modelling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network","publication_year":2023,"publication_date":"2023-05-16","ids":{"openalex":"https://openalex.org/W4376988750","doi":"https://doi.org/10.48550/arxiv.2305.09156"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.09156","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.09156","pdf_url":"https://arxiv.org/pdf/2305.09156","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/2305.09156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055322544","display_name":"Zitang Sun","orcid":"https://orcid.org/0000-0003-2267-421X","observed_orcids":["https://orcid.org/0000-0003-2267-421X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zitang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613276","display_name":"Yen\u2010Ju Chen","orcid":"https://orcid.org/0000-0002-2038-1440","observed_orcids":["https://orcid.org/0000-0002-2038-1440"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yen-Ju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070899835","display_name":"Yung\u2010Hao Yang","orcid":"https://orcid.org/0000-0002-6684-6274","observed_orcids":["https://orcid.org/0000-0002-6684-6274"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yung-hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102989550","display_name":"Shin\u2019ya Nishida","orcid":"https://orcid.org/0000-0002-5098-4752","observed_orcids":["https://orcid.org/0000-0002-5098-4752"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishida, Shin'ya","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":2,"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.009499999694526196,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.001500000013038516,"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/visual-motion-perception","display_name":"visual motion perception","score":0.7990000247955322},{"id":"https://openalex.org/keywords/self-attention-network","display_name":"self-attention network","score":0.8420000076293945},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7379999756813049},{"id":"https://openalex.org/keywords/optical-flow","display_name":"optical flow","score":0.6399999856948853},{"id":"https://openalex.org/keywords/speed-tuning","display_name":"velocity tuning","score":0.7639999985694885}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7015796899795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781173944473267},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.577765703201294},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.5743938088417053},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5623243451118469},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5344229340553284},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.5342572927474976},{"id":"https://openalex.org/C48575856","wikidata":"https://www.wikidata.org/wiki/Q852504","display_name":"Motion perception","level":3,"score":0.5201923847198486},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.49402981996536255},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4926601052284241},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4765527844429016},{"id":"https://openalex.org/C152478114","wikidata":"https://www.wikidata.org/wiki/Q660910","display_name":"Neurophysiology","level":2,"score":0.47242867946624756},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.4349464178085327},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.15559953451156616},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12963074445724487},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12323427200317383}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.09156","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.09156","pdf_url":"https://arxiv.org/pdf/2305.09156","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.09156","doi":"https://doi.org/10.48550/arxiv.2305.09156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.09156","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":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:2305.09156","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.09156","pdf_url":"https://arxiv.org/pdf/2305.09156","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.75}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2162216530","https://openalex.org/W2099247362","https://openalex.org/W2139003580","https://openalex.org/W2936229268","https://openalex.org/W2983684151","https://openalex.org/W2179317868","https://openalex.org/W2346394970","https://openalex.org/W2009953394","https://openalex.org/W2090216735","https://openalex.org/W4206806707"],"abstract_inverted_index":{"Visual":[0],"motion":[1,26,69,79,100,110,128,142,170,230],"processing":[2,38],"is":[3],"essential":[4],"for":[5,108,127,144],"humans":[6],"to":[7,41,57,68,118,139,165,183],"perceive":[8],"and":[9,87,112,172],"interact":[10],"with":[11,35,103,227],"dynamic":[12],"environments.":[13],"Despite":[14],"extensive":[15],"research":[16],"in":[17,31,47,60,122,130,189],"cognitive":[18],"neuroscience,":[19],"image-computable":[20,75],"models":[21,216],"that":[22,97,158,201],"can":[23,178],"extract":[24],"informative":[25,141],"flow":[27,62,143],"from":[28],"natural":[29,152],"scenes":[30],"a":[32,64,93,104,145,184,223],"manner":[33],"consistent":[34,226],"human":[36,78,181,205,228],"visual":[37,133,229],"have":[39,55],"yet":[40],"be":[42,238],"established.":[43],"Meanwhile,":[44],"recent":[45],"advancements":[46],"computer":[48],"vision":[49],"(CV),":[50],"propelled":[51],"by":[52,81],"deep":[53],"learning,":[54],"led":[56],"significant":[58],"progress":[59],"optical":[61],"estimation,":[63],"task":[65],"closely":[66],"related":[67],"perception.":[70],"Here":[71],"we":[72,91],"propose":[73],"an":[74],"model":[76,115,177,203],"of":[77,148,186],"perception":[80,129],"bridging":[82],"the":[83,120,124,131,137,197,209,213,218,233],"gap":[84],"between":[85],"biological":[86,132],"CV":[88,215],"models.":[89],"Specifically,":[90],"introduce":[92],"novel":[94],"two-stages":[95],"approach":[96],"combines":[98],"trainable":[99],"energy":[101],"sensing":[102],"recurrent":[105],"self-attention":[106],"network":[107],"adaptive":[109],"integration":[111],"segregation.":[113],"This":[114],"architecture":[116,225],"aims":[117],"capture":[119],"computations":[121],"V1-MT,":[123],"core":[125],"structure":[126],"system,":[134],"while":[135],"providing":[136],"ability":[138],"derive":[140],"wide":[146],"range":[147,185],"stimuli,":[149],"including":[150],"complex":[151],"scenes.":[153],"In":[154],"silico":[155],"neurophysiology":[156],"reveals":[157],"our":[159,202],"model's":[160],"unit":[161],"responses":[162,182,206],"are":[163],"similar":[164],"mammalian":[166],"neural":[167],"recordings":[168],"regarding":[169],"pooling":[171],"speed":[173],"tuning.":[174],"The":[175,193],"proposed":[176],"also":[179],"replicate":[180],"stimuli":[187],"examined":[188],"past":[190],"psychophysical":[191],"studies.":[192],"experimental":[194],"results":[195],"on":[196],"Sintel":[198],"benchmark":[199],"demonstrate":[200],"predicts":[204],"better":[207],"than":[208],"ground":[210],"truth,":[211],"whereas":[212],"state-of-the-art":[214],"show":[217],"opposite.":[219],"Our":[220],"study":[221],"provides":[222],"computational":[224],"processing,":[231],"although":[232],"physiological":[234],"correspondence":[235],"may":[236],"not":[237],"exact.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2025-10-10T00:00:00"}