{"id":"https://openalex.org/W4416157668","doi":"https://doi.org/10.1109/wacv61042.2026.00461","title":"Countering Multi-modal Representation Collapse through Rank-targeted Fusion","display_name":"Countering Multi-modal Representation Collapse through Rank-targeted Fusion","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416157668","doi":"https://doi.org/10.1109/wacv61042.2026.00461"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.06450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084999063","display_name":"Seul\u2010Gi Kim","orcid":"https://orcid.org/0000-0003-1641-4059"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seulgi Kim","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059939248","display_name":"Kiran Kokilepersaud","orcid":"https://orcid.org/0000-0001-6225-2455"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiran Kokilepersaud","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010958338","display_name":"Mohit Prabhushankar","orcid":"https://orcid.org/0000-0002-8743-7058"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Prabhushankar","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006145139","display_name":"Ghassan AlRegib","orcid":"https://orcid.org/0000-0001-6818-8001"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghassan AlRegib","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00915127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4744","last_page":"4754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5486000180244446,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.5486000180244446,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10830000042915344,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.03889999911189079,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7440999746322632},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6510000228881836},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6384999752044678},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6340000033378601},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4627000093460083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4426000118255615},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4406000077724457}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6384999752044678},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6340000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6133000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.567799985408783},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wacv61042.2026.00461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.06450","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.06450","pdf_url":"https://arxiv.org/pdf/2511.06450","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2511.06450","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2511.06450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.06450","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.06450","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.06450","pdf_url":"https://arxiv.org/pdf/2511.06450","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"fusion":[1,116,188],"methods":[2,55,205],"often":[3],"suffer":[4],"from":[5,124,130],"two":[6],"types":[7],"of":[8,89,142],"representation":[9,106],"collapse:":[10],"feature":[11,49,59,76],"collapse":[12,26,60,63,79],"where":[13,27,182],"individual":[14],"dimensions":[15],"lose":[16],"their":[17],"discriminative":[18],"power":[19],"(as":[20],"measured":[21],"by":[22,47,206],"eigenspectra),":[23],"and":[24,50,61,77,102,195],"modality":[25,30,51,62,78,126,148,152,173],"one":[28,125],"dominant":[29],"overwhelms":[31],"the":[32,87,105,139,143],"other.":[33],"Applications":[34],"like":[35],"human":[36],"action":[37,180],"anticipation":[38],"that":[39,73,96,118,135,154,163,198],"require":[40],"fusing":[41],"multifarious":[42],"sensor":[43],"data":[44],"are":[45],"hindered":[46],"both":[48,104],"collapse.":[52,174],"However,":[53],"existing":[54],"attempt":[56],"to":[57,100,208],"counter":[58,103],"separately.":[64],"This":[65],"is":[66,69,212],"because":[67],"there":[68],"no":[70],"unifying":[71],"framework":[72,117],"efficiently":[74],"addresses":[75],"in":[80],"conjunction.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,150,183],"posit":[86],"utility":[88],"effective":[90,140,159],"rank":[91,141],"as":[92],"an":[93],"informative":[94,122],"measure":[95],"can":[97],"be":[98],"utilized":[99],"quantify":[101],"collapses.":[107],"We":[108,133,161,175],"propose":[109],"Rank-enhancing":[110],"Token":[111],"Fuser,":[112],"a":[113,186],"theoretically":[114],"grounded":[115],"selectively":[119],"blends":[120],"less":[121],"features":[123,129],"with":[127,170],"complementary":[128],"another":[131],"modality.":[132],"show":[134,162],"our":[136,177,199],"method":[137,178],"increases":[138],"fused":[144,169],"representation.":[145],"To":[146],"address":[147],"collapse,":[149],"evaluate":[151],"combinations":[153],"mutually":[155],"increase":[156],"each":[157],"others\u2019":[158],"rank.":[160],"depth":[164],"maintains":[165],"representational":[166],"balance":[167],"when":[168],"RGB,":[171],"avoiding":[172],"validate":[176],"on":[179,192],"anticipation,":[181],"present":[184],"R3D,":[185],"depth-informed":[187],"framework.":[189],"Extensive":[190],"experiments":[191],"NTURGBD,":[193],"UTKinect,":[194],"DARai":[196],"demonstrate":[197],"approach":[200],"significantly":[201],"outperforms":[202],"prior":[203],"state-of-the-art":[204],"up":[207],"3.74%.":[209],"Our":[210],"code":[211],"available":[213],"at:":[214],"https://github.com/olivesgatech/R3D.":[215]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-12T00:00:00"}