{"id":"https://openalex.org/W4414360625","doi":"https://doi.org/10.24963/ijcai.2025/144","title":"UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block","display_name":"UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360625","doi":"https://doi.org/10.24963/ijcai.2025/144"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/144","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080392501","display_name":"Luoxi Jing","orcid":"https://orcid.org/0000-0002-1540-5815"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luoxi Jing","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":["https://openalex.org/I4210165407"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044574026","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0002-7685-5457"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707142","display_name":"Songchang Jin","orcid":"https://orcid.org/0000-0002-5959-0768"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Songchang Jin","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072647192","display_name":"Chunping Qiu","orcid":"https://orcid.org/0000-0002-7109-5559"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Chunping Qiu","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056151170","display_name":"Ziteng Qiao","orcid":"https://orcid.org/0000-0002-2414-0062"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ziteng Qiao","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724210","display_name":"Yuxian Li","orcid":"https://orcid.org/0000-0001-9023-0894"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxian Li","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071223948","display_name":"Jianqiang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Xia","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1287","last_page":"1295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9943000078201294,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/monocular","display_name":"Monocular","score":0.448199987411499},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44760000705718994},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.3952000141143799},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.392300009727478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3758000135421753},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3652999997138977},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33970001339912415},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.320499986410141}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7531999945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077000141143799},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.63919997215271},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3952000141143799},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2780056265","wikidata":"https://www.wikidata.org/wiki/Q106239881","display_name":"High dynamic range","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C77246614","wikidata":"https://www.wikidata.org/wiki/Q1409400","display_name":"Gramian matrix","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/144","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Depth":[0,158],"estimation":[1,167],"plays":[2],"a":[3,15],"crucial":[4],"role":[5],"in":[6,14,24],"3D":[7],"scene":[8],"understanding":[9],"and":[10,34,45,63,95,100,126,149,163],"is":[11],"extensively":[12],"used":[13],"wide":[16],"range":[17,33],"of":[18],"vision":[19],"tasks.":[20],"Image-based":[21],"methods":[22,59,74,168],"struggle":[23,60],"challenging":[25],"scenarios,":[26],"while":[27,71],"event":[28,44],"cameras":[29],"offer":[30],"high":[31],"dynamic":[32],"temporal":[35],"resolution":[36],"but":[37],"face":[38],"difficulties":[39],"with":[40,61],"sparse":[41],"data.":[42],"Combining":[43],"image":[46],"data":[47],"provides":[48],"significant":[49],"advantages,":[50],"yet":[51],"effective":[52,132],"integration":[53],"remains":[54],"challenging.":[55],"Existing":[56],"CNN-based":[57],"fusion":[58,73,90],"occlusions":[62],"depth":[64,166],"disparities":[65],"due":[66],"to":[67,97,122,145],"limited":[68],"receptive":[69],"fields,":[70],"Transformer-based":[72],"often":[75],"lack":[76],"deep":[77],"modality":[78],"interaction.":[79],"To":[80],"address":[81],"these":[82],"issues,":[83],"we":[84,136],"propose":[85,104],"UniCT":[86,157],"Depth,":[87],"an":[88],"event-image":[89],"method":[91],"that":[92,156],"unifies":[93],"CNNs":[94],"Transformers":[96],"model":[98],"local":[99],"global":[101],"features.":[102],"We":[103],"the":[105,114,138],"Convolution-compensated":[106],"ViT":[107],"Dual":[108],"SA":[109],"(CcViT-DA)":[110],"Block,":[111],"designed":[112],"for":[113,131],"encoder,":[115],"which":[116],"integrates":[117],"Context":[118],"Modeling":[119],"Self-Attention":[120,129],"(CMSA)":[121],"capture":[123],"spatial":[124],"dependencies":[125],"Modal":[127],"Fusion":[128],"(MFSA)":[130],"cross-modal":[133],"fusion.":[134],"Furthermore,":[135],"design":[137],"tailored":[139],"Detail":[140],"Compensation":[141],"Convolution":[142],"(DCC)":[143],"Block":[144],"improve":[146],"texture":[147],"details":[148],"enhances":[150],"edge":[151],"representations.":[152],"Extensive":[153],"experiments":[154],"show":[155],"outperforms":[159],"existing":[160],"image,":[161],"event,":[162],"fusion-based":[164],"monocular":[165],"across":[169],"key":[170],"metrics.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}