{"id":"https://openalex.org/W4322618045","doi":"https://doi.org/10.48550/arxiv.2302.12589","title":"Revisiting Modality Imbalance In Multimodal Pedestrian Detection","display_name":"Revisiting Modality Imbalance In Multimodal Pedestrian Detection","publication_year":2023,"publication_date":"2023-02-24","ids":{"openalex":"https://openalex.org/W4322618045","doi":"https://doi.org/10.48550/arxiv.2302.12589"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2302.12589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.12589","pdf_url":"https://arxiv.org/pdf/2302.12589","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.12589","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019925147","display_name":"Arindam Das","orcid":"https://orcid.org/0000-0001-6139-9922"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Das, Arindam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703255","display_name":"Sudip Das","orcid":"https://orcid.org/0000-0002-8372-4316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Sudip","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104346398","display_name":"Ganesh Sistu","orcid":"https://orcid.org/0009-0003-1683-9257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sistu, Ganesh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030416087","display_name":"Jonathan Horgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horgan, Jonathan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090127362","display_name":"Ujjwal Bhattacharya","orcid":"https://orcid.org/0000-0002-8546-6453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhattacharya, Ujjwal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008448972","display_name":"Edward Jones","orcid":"https://orcid.org/0000-0003-1521-4442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jones, Edward","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053838927","display_name":"Martin Glavin","orcid":"https://orcid.org/0000-0003-1477-4835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Glavin, Martin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084975687","display_name":"Ciar\u00e1n Eising","orcid":"https://orcid.org/0000-0001-8383-2635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eising, Ciar\u00e1n","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5019925147"],"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962000250816345,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962000250816345,"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":0.9902999997138977,"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748175859451294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6577402353286743},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6167758107185364},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6116766929626465},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5792035460472107},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5436018109321594},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4912993311882019},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47592049837112427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07413831353187561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748175859451294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6577402353286743},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6167758107185364},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6116766929626465},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5792035460472107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5436018109321594},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4912993311882019},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47592049837112427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07413831353187561},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2302.12589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.12589","pdf_url":"https://arxiv.org/pdf/2302.12589","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.12589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.12589","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.12589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.12589","pdf_url":"https://arxiv.org/pdf/2302.12589","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4322618045.pdf","grobid_xml":"https://content.openalex.org/works/W4322618045.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multimodal":[0],"learning,":[1],"particularly":[2],"for":[3],"pedestrian":[4],"detection,":[5],"has":[6],"recently":[7],"received":[8],"emphasis":[9],"due":[10],"to":[11,14,76,94,109,128,136],"its":[12],"capability":[13],"function":[15],"equally":[16],"well":[17],"in":[18,33,90],"several":[19],"critical":[20],"autonomous":[21],"driving":[22],"scenarios":[23],"such":[24,59],"as":[25,137],"low-light,":[26],"night-time,":[27],"and":[28,168],"adverse":[29],"weather":[30],"conditions.":[31],"However,":[32],"most":[34],"cases,":[35],"the":[36,41,49,56,66,77,91,96,102,111,120,126,130,139,150,155,163,174],"training":[37,71,86,127],"distribution":[38,132],"largely":[39],"emphasizes":[40],"contribution":[42],"of":[43,58,79,98,146,162,173],"one":[44,53],"specific":[45],"input":[46,68],"that":[47],"makes":[48],"network":[50],"biased":[51],"towards":[52],"modality.":[54],"Hence,":[55],"generalization":[57],"models":[60],"becomes":[61],"a":[62,84],"significant":[63],"problem":[64,97],"where":[65],"non-dominant":[67],"modality":[69],"during":[70,125],"could":[72],"be":[73],"contributing":[74],"more":[75,115],"course":[78],"inference.":[80],"Here,":[81],"we":[82],"introduce":[83],"novel":[85],"setup":[87],"with":[88],"regularizer":[89,106],"multimodal":[92,131],"architecture":[93],"resolve":[95],"this":[99],"disparity":[100],"between":[101],"modalities.":[103],"Specifically,":[104],"our":[105,143],"term":[107],"helps":[108,149],"make":[110],"feature":[112,121],"fusion":[113],"method":[114,165],"robust":[116],"by":[117,153],"considering":[118],"both":[119],"extractors":[122],"equivalently":[123],"important":[124],"extract":[129],"which":[133],"is":[134],"referred":[135],"removing":[138],"imbalance":[140],"problem.":[141],"Furthermore,":[142],"decoupling":[144],"concept":[145],"output":[147],"stream":[148],"detection":[151],"task":[152],"sharing":[154],"spatial":[156],"sensitive":[157],"information":[158],"mutually.":[159],"Extensive":[160],"experiments":[161],"proposed":[164],"on":[166],"KAIST":[167],"UTokyo":[169],"datasets":[170],"shows":[171],"improvement":[172],"respective":[175],"state-of-the-art":[176],"performance.":[177]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}