{"id":"https://openalex.org/W7131069047","doi":"https://doi.org/10.1109/iccvw69036.2025.00492","title":"Multimodal Neuromorphic Event-Frame Fusion in Domain-Generalized Vision Transformer for Dynamic Object Tracking","display_name":"Multimodal Neuromorphic Event-Frame Fusion in Domain-Generalized Vision Transformer for Dynamic Object Tracking","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131069047","doi":"https://doi.org/10.1109/iccvw69036.2025.00492"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106834687","display_name":"Taha Razzaq","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Taha Razzaq","raw_affiliation_strings":["Tibbling Technologies"],"affiliations":[{"raw_affiliation_string":"Tibbling Technologies","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124948532","display_name":"Asim Iqbal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asim Iqbal","raw_affiliation_strings":["Tibbling Technologies"],"affiliations":[{"raw_affiliation_string":"Tibbling Technologies","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106834687"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66241938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4743","last_page":"4750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.4422999918460846,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.4422999918460846,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.06539999693632126,"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":0.03229999914765358,"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/neuromorphic-engineering","display_name":"Neuromorphic engineering","score":0.8536999821662903},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5559999942779541},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49160000681877136},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4844000041484833},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.48019999265670776},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4677000045776367},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.45989999175071716},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4115000069141388}],"concepts":[{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.8536999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7588000297546387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7232999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073000073432922},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4844000041484833},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.48019999265670776},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4677000045776367},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.35409998893737793},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C76935873","wikidata":"https://www.wikidata.org/wiki/Q209121","display_name":"Image sensor","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2138787968","https://openalex.org/W2601564443","https://openalex.org/W2962927175","https://openalex.org/W2997563066","https://openalex.org/W3040838455","https://openalex.org/W3178334627","https://openalex.org/W3189897383","https://openalex.org/W3202534481","https://openalex.org/W4296549969","https://openalex.org/W4313046728","https://openalex.org/W4383066213","https://openalex.org/W4385815464","https://openalex.org/W4386075741","https://openalex.org/W4390871749","https://openalex.org/W4390872684","https://openalex.org/W4390872749","https://openalex.org/W4402715800","https://openalex.org/W4404612908","https://openalex.org/W4416016665"],"related_works":[],"abstract_inverted_index":{"Object":[0],"tracking":[1,20,159],"is":[2],"a":[3,43,61,187,193],"fundamental":[4],"task":[5],"in":[6,12,23,53,155,162],"computer":[7],"vision":[8,58],"with":[9,164],"critical":[10],"applications":[11],"autonomous":[13],"driving,":[14],"surveillance,":[15],"and":[16,98,158,168],"robotics.":[17],"However,":[18,56],"existing":[19],"solutions":[21],"struggle":[22],"high-speed,":[24],"real-time":[25,199],"scenarios":[26],"due":[27],"to":[28,68,83,113,117],"their":[29,66],"reliance":[30],"on":[31,121,186],"conventional":[32],"frame-based":[33],"sensors":[34,41,59],"optimized":[35],"for":[36,73,180],"low-frame-rate":[37],"environments.":[38],"Neuromorphic":[39],"event-driven":[40],"offer":[42],"compute-efficient":[44],"alternative":[45],"by":[46],"capturing":[47],"continuous,":[48],"asynchronous":[49],"intensity":[50],"changes,":[51],"excelling":[52],"fast-motion":[54],"detection.":[55],"neuromorphic":[57],"have":[60,79],"lower":[62],"spatial":[63],"resolution,":[64],"limiting":[65],"ability":[67],"capture":[69],"fine":[70],"textures":[71],"crucial":[72],"object":[74,156,200],"identification.":[75],"Multimodal":[76],"fusion":[77,103,204],"techniques":[78],"been":[80],"explored":[81],"recently":[82],"leverage":[84],"the":[85,145,203],"complementary":[86],"strengths":[87],"of":[88,134,205],"both":[89],"frames+events":[90],"modalities,":[91],"incorporating":[92],"optical":[93],"flow":[94],"estimation,":[95],"motion":[96],"compensation,":[97],"deformable":[99],"convolutions.":[100],"While":[101],"these":[102],"models":[104],"improve":[105],"performance":[106,179],"under":[107],"rapid":[108],"motion,":[109],"they":[110],"remain":[111],"susceptible":[112],"domain":[114,153],"shifts,":[115],"leading":[116],"degradation":[118],"when":[119,184],"tested":[120],"out-of-distribution":[122],"\u201cunseen\u201d":[123],"target":[124],"data.":[125,207],"To":[126],"address":[127],"this":[128],"challenge,":[129],"we":[130,191],"introduce":[131],"an":[132],"application":[133],"neuro-inspired,":[135],"domain-generalized":[136],"Winner-Take-All":[137],"(WTA)":[138],"mathematical":[139],"layer":[140],"that":[141,173,197],"seamlessly":[142],"integrates":[143],"into":[144],"Vision":[146],"Transformer":[147],"(ViT)":[148],"architecture.":[149],"Our":[150],"approach":[151],"enhances":[152],"invariance":[154],"detection":[157,201],"systems,":[160],"particularly":[161],"environments":[163],"diverse":[165],"lighting":[166],"conditions":[167],"visual":[169],"variations.":[170],"We":[171],"demonstrate":[172],"our":[174],"technique":[175],"significantly":[176],"improves":[177],"ViT":[178],"image":[181],"classification,":[182],"even":[183],"trained":[185],"limited":[188],"dataset.":[189],"Additionally,":[190],"propose":[192],"multimodal":[194],"AI":[195],"framework":[196],"enables":[198],"through":[202],"frame+event-based":[206]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}