{"id":"https://openalex.org/W4416249993","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227211","title":"RGB-Event Fusion with Self-Attention for Collision Prediction","display_name":"RGB-Event Fusion with Self-Attention for Collision Prediction","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249993","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227211"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5092506176","display_name":"Pietro Bonazzi","orcid":"https://orcid.org/0009-0006-6147-2214"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pietro Bonazzi","raw_affiliation_strings":["ETH Zürich,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich,Zürich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024319570","display_name":"Christian Vogt","orcid":"https://orcid.org/0000-0003-4551-4876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Vogt","raw_affiliation_strings":["ETH Zürich,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich,Zürich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110073999","display_name":"Michael Jost","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Jost","raw_affiliation_strings":["ETH Zürich,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich,Zürich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044945190","display_name":"Haotong Qin","orcid":"https://orcid.org/0000-0001-7391-7539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haotong Qin","raw_affiliation_strings":["ETH Zürich,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich,Zürich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020816441","display_name":"Lyes Khacef","orcid":"https://orcid.org/0000-0002-4009-174X"},"institutions":[{"id":"https://openalex.org/I1304132090","display_name":"Sony (Taiwan)","ror":"https://ror.org/0214y7014","country_code":"TW","type":"company","lineage":["https://openalex.org/I1304132090","https://openalex.org/I4210143797"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lyes Khacef","raw_affiliation_strings":["Sony Europe B.V.,Sony Semiconductor Solutions Europe,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Sony Semiconductor Solutions Europe,Zürich,Switzerland","institution_ids":["https://openalex.org/I1304132090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045868980","display_name":"Federico Paredes-Vall\u00e9s","orcid":"https://orcid.org/0000-0002-9478-7195"},"institutions":[{"id":"https://openalex.org/I1304132090","display_name":"Sony (Taiwan)","ror":"https://ror.org/0214y7014","country_code":"TW","type":"company","lineage":["https://openalex.org/I1304132090","https://openalex.org/I4210143797"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Federico Paredes-Valles","raw_affiliation_strings":["Sony Europe B.V.,Sony Semiconductor Solutions Europe,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Sony Semiconductor Solutions Europe,Zürich,Switzerland","institution_ids":["https://openalex.org/I1304132090"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066423975","display_name":"Michele Magno","orcid":"https://orcid.org/0000-0003-0368-8923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele Magno","raw_affiliation_strings":["ETH Zürich,Zürich,Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich,Zürich,Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5092506176"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36616582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.4284999966621399,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.4284999966621399,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.14890000224113464,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.1200999990105629,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/leverage","display_name":"Leverage (statistics)","score":0.6499999761581421},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6445000171661377},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5717999935150146},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5285999774932861},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5026000142097473},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.47760000824928284},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4602000117301941},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.45170000195503235}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6863999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6534000039100647},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6499999761581421},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4909000098705292},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.37869998812675476},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2777016798","wikidata":"https://www.wikidata.org/wiki/Q2001988","display_name":"Collision avoidance system","level":4,"score":0.3361000120639801},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.3296999931335449},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1957655654","https://openalex.org/W2021027097","https://openalex.org/W2964176059","https://openalex.org/W3011524659","https://openalex.org/W3034297393","https://openalex.org/W3035183452","https://openalex.org/W3040838455","https://openalex.org/W3091146474","https://openalex.org/W3095560049","https://openalex.org/W3104151879","https://openalex.org/W3129601843","https://openalex.org/W3134027214","https://openalex.org/W3198428947","https://openalex.org/W3202883604","https://openalex.org/W3205269907","https://openalex.org/W4213429939","https://openalex.org/W4281749192","https://openalex.org/W4296549969","https://openalex.org/W4382935244","https://openalex.org/W4383108925","https://openalex.org/W4383172048","https://openalex.org/W4385488572","https://openalex.org/W4385801369","https://openalex.org/W4390873758","https://openalex.org/W4395447485","https://openalex.org/W4396917670","https://openalex.org/W4398197727","https://openalex.org/W4402351350","https://openalex.org/W4402916012","https://openalex.org/W4402917147","https://openalex.org/W4403798244","https://openalex.org/W4405779046","https://openalex.org/W4405785050","https://openalex.org/W4407386505","https://openalex.org/W4414198244"],"related_works":[],"abstract_inverted_index":{"Ensuring":[0],"robust":[1],"and":[2,30,44,85,115,130,147,182,194],"real-time":[3],"obstacle":[4],"avoidance":[5],"is":[6],"critical":[7],"for":[8,26,58,117,145,149],"the":[9,28,74,88,94,99,124,136,140,167,177,187],"safe":[10],"operation":[11],"of":[12,33,52,83,92,111,126,166,189],"autonomous":[13],"robots":[14],"in":[15,105,128,133,197],"dynamic,":[16],"real-world":[17],"environments.":[18],"This":[19],"paper":[20],"proposes":[21],"a":[22,39,153,159],"neural":[23],"network":[24],"framework":[25],"predicting":[27],"time":[29,150],"collision":[31],"position":[32,146],"an":[34,103],"unmanned":[35],"aerial":[36],"vehicle":[37],"with":[38],"dynamic":[40],"object,":[41],"using":[42,192],"RGB":[43,141,193],"event-based":[45,137,168,195],"vision":[46],"sensors.":[47],"The":[48],"proposed":[49],"architecture":[50],"consists":[51],"two":[53],"separate":[54],"encoder":[55],"branches,":[56],"one":[57],"each":[59],"modality,":[60],"followed":[61],"by":[62,64,143],"fusion":[63],"self-attention":[65],"to":[66,172,175],"improve":[67],"prediction":[68,90,106],"accuracy.To":[69],"facilitate":[70],"benchmarking,":[71],"we":[72,162],"leverage":[73],"ABCD":[75],"[8]":[76],"dataset":[77],"collected":[78],"that":[79,98],"enables":[80],"detailed":[81],"comparisons":[82],"single-modality":[84,109],"fusion-based":[86,100],"approaches.At":[87],"same":[89],"throughput":[91],"50Hz,":[93],"experimental":[95],"results":[96],"show":[97],"model":[101,138,142],"offers":[102],"improvement":[104],"accuracy":[107],"over":[108],"approaches":[110],"1%":[112],"on":[113],"average":[114],"10%":[116],"distances":[118],"beyond":[119],"0.5m,":[120],"but":[121],"comes":[122],"at":[123,152],"cost":[125],"+71%":[127],"memory":[129],"+":[131],"105%":[132],"FLOPs.":[134],"Notably,":[135],"outperforms":[139],"4%":[144],"26%":[148],"error":[151],"similar":[154],"computational":[155,183],"cost,":[156],"making":[157],"it":[158],"competitive":[160],"alternative.Additionally,":[161],"evaluate":[163],"quantized":[164],"versions":[165],"models,":[169],"applying":[170],"1-":[171],"8-bit":[173],"quantization":[174],"assess":[176],"trade-offs":[178,188],"between":[179],"predictive":[180],"performance":[181],"efficiency.These":[184],"findings":[185],"highlight":[186],"multi-modal":[190],"perception":[191],"cameras":[196],"robotic":[198],"applications.":[199]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}