{"id":"https://openalex.org/W7137352824","doi":"https://doi.org/10.1109/itsc60802.2025.11423431","title":"DSATFusion: Multi-Modal 3D Detection via Vision-Text Synergy with Dynamic Sparse Attention Temporal Fusion","display_name":"DSATFusion: Multi-Modal 3D Detection via Vision-Text Synergy with Dynamic Sparse Attention Temporal Fusion","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7137352824","doi":"https://doi.org/10.1109/itsc60802.2025.11423431"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","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/A5101624436","display_name":"Yiheng Zhang","orcid":"https://orcid.org/0009-0002-2426-0838"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiheng Zhang","raw_affiliation_strings":["School of Earth Science and Engineering, Hohai University,Nanjing,China,211100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Earth Science and Engineering, Hohai University,Nanjing,China,211100","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Pei Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895","https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129560588","display_name":"Haipeng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Haipeng Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895","https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697068","display_name":"Xiaohu Liu","orcid":"https://orcid.org/0000-0002-8973-438X"},"institutions":[{"id":"https://openalex.org/I135836153","display_name":"Shenyang Agricultural University","ror":"https://ror.org/01n7x9n08","country_code":"CN","type":"education","lineage":["https://openalex.org/I135836153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Liu","raw_affiliation_strings":["College of Land and Environment, Shenyang Agricultural University,Shenyang,China,110866"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Land and Environment, Shenyang Agricultural University,Shenyang,China,110866","institution_ids":["https://openalex.org/I135836153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007085564","display_name":"Minghua Huang","orcid":"https://orcid.org/0000-0002-8140-2436"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Huang","raw_affiliation_strings":["School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China,222005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China,222005","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129532552","display_name":"Junlan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Chen","raw_affiliation_strings":["Southeast University,Nanjing,China,211189"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,211189","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087453468","display_name":"Shandong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shandong Wang","raw_affiliation_strings":["College of Geography and Remote Sensing, Hohai University,Nanjing,China,211100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Geography and Remote Sensing, Hohai University,Nanjing,China,211100","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4275","last_page":"4282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.454800009727478,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.454800009727478,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.19290000200271606,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.05849999934434891,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4401000142097473},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3564999997615814},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3257000148296356},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.32199999690055847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29179999232292175}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6092000007629395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5807999968528748},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45179998874664307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23319999873638153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2946567085","https://openalex.org/W3035574168","https://openalex.org/W3109395584","https://openalex.org/W3215100485","https://openalex.org/W4225793049","https://openalex.org/W4225922615","https://openalex.org/W4310557340","https://openalex.org/W4382450829","https://openalex.org/W4382464460","https://openalex.org/W4386072002","https://openalex.org/W4386075524","https://openalex.org/W4386075580","https://openalex.org/W4390872833","https://openalex.org/W4390873371","https://openalex.org/W4390874598","https://openalex.org/W4396941548","https://openalex.org/W4402727605","https://openalex.org/W4404443080","https://openalex.org/W4409917508"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"query-based":[1],"paradigms":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"success":[6],"in":[7,25,138,191],"multi-view":[8],"3D":[9,194],"detection":[10,30,149,195],"for":[11,174],"autonomous":[12],"driving":[13],"systems.":[14],"However,":[15],"they":[16],"remain":[17],"constrained":[18],"by":[19],"two":[20],"critical":[21,70],"limitations:":[22],"computational":[23,64],"redundancy":[24],"complex":[26,143],"scenes":[27],"and":[28,78,98,164],"ineffective":[29],"of":[31,82,120,133,150,186],"long-tail":[32,151],"categories.":[33],"To":[34],"address":[35,147],"these":[36],"challenges,":[37],"we":[38,86,153],"propose":[39],"DSATFusion,":[40,187],"a":[41,51,88,155,159],"novel":[42],"dynamic":[43,52],"sparse":[44,53,60],"attention":[45,54,91],"temporal":[46,76,90,123,134],"fusion":[47,92,128],"framework.":[48],"DSATFusion":[49],"leverages":[50],"network":[55],"to":[56,73,106,146],"dynamically":[57,96],"identify":[58],"regionspecific":[59],"features,":[61,102],"significantly":[62,169],"reducing":[63],"overhead":[65],"while":[66,109],"maintaining":[67],"focus":[68],"on":[69,179],"regions.":[71],"Furthermore,":[72],"effectively":[74],"harness":[75],"information":[77,124],"tackle":[79],"the":[80,111,131,148,180,184],"challenges":[81],"long-term":[83,122],"sequence":[84,135],"modeling,":[85,136],"introduce":[87],"recurring":[89],"strategy.":[93],"This":[94,167],"approach":[95],"weights":[97],"fuses":[99],"historical":[100],"frame":[101],"ensuring":[103],"continuous":[104],"updates":[105],"target":[107],"representations":[108],"emphasizing":[110],"most":[112],"salient":[113],"objects":[114],"across":[115],"diverse":[116],"viewpoints.":[117],"The":[118],"integration":[119],"rich,":[121],"with":[125],"an":[126],"efficient":[127],"pipeline":[129],"enhances":[130],"robustness":[132],"particularly":[137],"scenarios":[139],"involving":[140],"occlusions":[141],"or":[142],"backgrounds.":[144],"Additionally,":[145],"categories,":[152],"incorporate":[154],"Vision-Language":[156],"Model,":[157],"establishing":[158],"similarity-driven":[160],"alignment":[161,168],"between":[162],"visual":[163],"textual":[165],"domains.":[166],"improves":[170],"fine-grained":[171],"classification":[172],"accuracy":[173],"rare-class":[175],"objects.":[176],"Extensive":[177],"experiments":[178],"nuScenes":[181],"benchmark":[182],"demonstrate":[183],"efficacy":[185],"achieving":[188],"state-of-the-art":[189],"performance":[190],"various":[192],"camera-based":[193],"tasks.":[196]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-17T00:00:00"}