{"id":"https://openalex.org/W7139022853","doi":"https://doi.org/10.1145/3788149.3788248","title":"Lightweight Multi-Modal Framework for 3D Object Detection and Localization","display_name":"Lightweight Multi-Modal Framework for 3D Object Detection and Localization","publication_year":2025,"publication_date":"2025-12-12","ids":{"openalex":"https://openalex.org/W7139022853","doi":"https://doi.org/10.1145/3788149.3788248"},"language":null,"primary_location":{"id":"doi:10.1145/3788149.3788248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788149.3788248","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788149.3788248","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129923435","display_name":"Yuran Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuran Zhang","raw_affiliation_strings":["State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1672-6014","affiliations":[{"raw_affiliation_string":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenguang Li","orcid":"https://orcid.org/0009-0001-3054-6691"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Li","raw_affiliation_strings":["State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3054-6691","affiliations":[{"raw_affiliation_string":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130150491","display_name":"Lingling Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhou","raw_affiliation_strings":["State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-2678-6091","affiliations":[{"raw_affiliation_string":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130141449","display_name":"Bin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-0281-1589","affiliations":[{"raw_affiliation_string":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China","institution_ids":["https://openalex.org/I17442442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17442442"],"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":"361","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3321000039577484,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3321000039577484,"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":0.061400000005960464,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.035599999129772186,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/object-detection","display_name":"Object detection","score":0.48010000586509705},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3253999948501587},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29280000925064087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29030001163482666}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.628600001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104999780654907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5795000195503235},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48010000586509705},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.2856999933719635},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788149.3788248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788149.3788248","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788149.3788248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788149.3788248","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2897529137","https://openalex.org/W3035346742","https://openalex.org/W3035461736","https://openalex.org/W4405429257"],"related_works":[],"abstract_inverted_index":{"Object":[0],"detection":[1,48],"and":[2,19,38,45,49,66,84,94,105,116,125,141,156,159,183,186,205,223,233,251,256],"global":[3,61,199,257],"localization":[4],"play":[5],"a":[6,28,53,173,202],"central":[7],"role":[8],"in":[9,14,121,197,253],"robotics,":[10],"with":[11,102],"wide":[12],"applications":[13],"autonomous":[15],"driving,":[16],"intelligent":[17],"navigation,":[18],"semantic-level":[20],"3D":[21,39,162,258],"scene":[22],"graph":[23],"construction.":[24],"This":[25],"paper":[26],"proposes":[27],"novel":[29],"lightweight":[30],"multi-modal":[31,254],"framework,":[32],"LiteFusion-Net,":[33],"which":[34],"fuses":[35],"RGB":[36],"camera":[37,155],"LiDAR":[40,157,170],"data":[41,158],"to":[42,60,63,80,97,128,133,194],"achieve":[43],"efficient":[44],"accurate":[46],"object":[47,178,259],"localization.":[50,260],"LiteFusion-Net":[51,211,239],"adopts":[52],"three-tiered":[54],"architecture,":[55],"progressing":[56],"from":[57],"local":[58],"perception":[59],"optimization":[62],"handle":[64],"outliers":[65],"ensure":[67],"overall":[68,208],"consistency":[69],"across":[70],"frames.":[71],"In":[72],"network":[73],"design,":[74],"Ghost":[75],"convolution":[76],"modules":[77],"are":[78],"introduced":[79],"reconstruct":[81],"the":[82,123,130,145,148,165,187,198],"backbone":[83,124],"feature":[85,100,220],"fusion":[86,126,146,255],"layers,":[87],"decomposing":[88],"standard":[89],"convolutions":[90],"into":[91,172],"linear":[92],"transformations":[93],"inexpensive":[95],"operations":[96],"generate":[98],"equivalent":[99],"maps":[101],"fewer":[103],"parameters":[104],"significantly":[106,244],"reduced":[107],"computational":[108,225],"complexity.":[109],"A":[110],"dual-dimensional":[111],"attention":[112],"mechanism,":[113],"combining":[114],"channel":[115],"spatial":[117,181],"attention,":[118],"is":[119,212],"embedded":[120],"both":[122],"layers":[127],"enhance":[129],"network\u2019s":[131],"ability":[132],"capture":[134],"salient":[135],"features":[136],"under":[137],"occlusion,":[138],"complex":[139],"backgrounds,":[140],"small-object":[142],"scenarios.":[143],"Regarding":[144],"strategy,":[147],"first":[149],"tier":[150,167,189],"performs":[151],"low-level":[152],"alignment":[153],"of":[154],"extracts":[160],"initial":[161],"bounding":[163],"boxes;":[164],"second":[166],"transforms":[168],"per-frame":[169],"detections":[171],"world":[174],"coordinate":[175],"system,":[176],"ensuring":[177],"uniqueness":[179],"via":[180],"matching":[182],"multi-view":[184],"fusion;":[185],"third":[188],"identifies":[190],"all":[191],"points":[192],"belonging":[193],"target":[195],"objects":[196],"map":[200],"through":[201,217],"point\u2013voxel":[203],"comparison":[204],"iteratively":[206],"optimizes":[207],"consistency.":[209],"Furthermore,":[210],"designed":[213],"for":[214],"edge":[215],"computing":[216],"parameter":[218],"compression,":[219],"redundancy":[221],"reduction,":[222],"module-level":[224],"optimization,":[226],"enabling":[227],"real-time":[228,246],"operation":[229],"on":[230],"resource-constrained":[231],"vehicle":[232],"robotic":[234],"platforms.":[235],"Experiments":[236],"demonstrate":[237],"that":[238],"achieves":[240],"high":[241],"accuracy":[242],"while":[243],"improving":[245],"performance,":[247],"validating":[248],"its":[249],"effectiveness":[250],"scalability":[252]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-20T00:00:00"}