{"id":"https://openalex.org/W4415541238","doi":"https://doi.org/10.1145/3746027.3754733","title":"Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection","display_name":"Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541238","doi":"https://doi.org/10.1145/3746027.3754733"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754733","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754733","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101348403","display_name":"Mingqian Ji","orcid":"https://orcid.org/0009-0006-1855-1945"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingqian Ji","raw_affiliation_strings":["PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924174","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-2984-8836"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412142","display_name":"Shanshan Zhang","orcid":"https://orcid.org/0000-0003-4013-6300"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Zhang","raw_affiliation_strings":["PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101348403"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32711277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"896","last_page":"904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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/lidar","display_name":"Lidar","score":0.6345000267028809},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.620199978351593},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5859000086784363},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5771999955177307},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5756999850273132},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4528999924659729},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43380001187324524}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8098000288009644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418000102043152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7041000127792358},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5756999850273132},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4706000089645386},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4131999909877777},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2678000032901764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754733","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754733","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2007046555","https://openalex.org/W2601243251","https://openalex.org/W2739781348","https://openalex.org/W2897529137","https://openalex.org/W2949708697","https://openalex.org/W2963182550","https://openalex.org/W2963849369","https://openalex.org/W2968296999","https://openalex.org/W2981949127","https://openalex.org/W2985406498","https://openalex.org/W3034314779","https://openalex.org/W3034681945","https://openalex.org/W3035160371","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3108975329","https://openalex.org/W3118341329","https://openalex.org/W3167095230","https://openalex.org/W3206335707","https://openalex.org/W3209102426","https://openalex.org/W4200632008","https://openalex.org/W4310078553","https://openalex.org/W4312253363","https://openalex.org/W4367182782","https://openalex.org/W4386065252","https://openalex.org/W4402727359"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"LiDAR-based":[1],"3D":[2,20,34,150],"object":[3,35],"detectors":[4],"typically":[5],"rely":[6],"on":[7,126,214,237],"manually":[8],"annotated":[9],"labels":[10,21,139],"for":[11,120],"training":[12],"to":[13,45,72,151,177,186],"achieve":[14],"good":[15],"performance.":[16],"However,":[17,49],"obtaining":[18],"high-quality":[19],"is":[22],"time-consuming":[23],"and":[24,60,87,107,123,128,161,168,182],"labor-intensive.":[25],"To":[26,91,156],"address":[27],"this":[28],"issue,":[29],"recent":[30],"works":[31],"explore":[32],"unsupervised":[33],"detection":[36],"by":[37,56,223,230],"introducing":[38],"RGB":[39,61,88,105],"images":[40,106,127],"as":[41,77],"an":[42,111],"auxiliary":[43],"modal":[44],"assist":[46],"pseudo-box":[47],"generation.":[48],"these":[50],"methods":[51,233],"simply":[52],"integrate":[53],"pseudo-boxes":[54,203],"generated":[55],"LiDAR":[57,86,108],"point":[58,154],"clouds":[59],"images.":[62],"Yet,":[63],"such":[64],"a":[65,98,130,166,193,205],"label-level":[66],"fusion":[67,101,132,195],"strategy":[68],"brings":[69],"limited":[70],"improvements":[71],"the":[73,80,93,141,215,220,238],"quality":[74],"of":[75,85],"pseudo-boxes,":[76],"it":[78],"overlooks":[79],"complementary":[81],"nature":[82],"in":[83],"terms":[84],"image":[89],"data.":[90],"overcome":[92],"above":[94],"limitations,":[95],"we":[96,115,164,191],"propose":[97,165,192],"novel":[99],"data-level":[100,194],"framework":[102],"that":[103,219,228],"integrates":[104],"data":[109],"at":[110],"early":[112],"stage.":[113],"Specifically,":[114],"utilize":[116],"vision":[117],"foundation":[118],"models":[119],"instance":[121],"segmentation":[122,162],"depth":[124,160,179],"estimation":[125,180],"introduce":[129],"bi-directional":[131],"method,":[133,171],"where":[134],"real":[135,153],"points":[136],"acquire":[137],"category":[138],"from":[140,159],"2D":[142,145],"space,":[143],"while":[144],"pixels":[146],"are":[147],"projected":[148],"onto":[149],"enhance":[152],"density.":[155],"mitigate":[157],"noise":[158],"estimations,":[163],"local":[167,174],"global":[169,183],"filtering":[170,176,185],"which":[172,200],"applies":[173],"radius":[175],"suppress":[178],"errors":[181],"statistical":[184],"remove":[187],"segmentation-induced":[188],"outliers.":[189],"Furthermore,":[190],"based":[196],"dynamic":[197],"self-evolution":[198],"strategy,":[199],"iteratively":[201],"refines":[202],"under":[204],"dense":[206],"representation,":[207],"significantly":[208,226],"improving":[209],"localization":[210],"accuracy.":[211],"Extensive":[212],"experiments":[213],"nuScenes":[216,239],"dataset":[217],"demonstrate":[218],"detector":[221],"trained":[222,229],"our":[224],"method":[225],"outperforms":[227],"previous":[231],"state-of-the-art":[232],"with":[234],"28.4%":[235],"mAP":[236],"validation":[240],"benchmark.":[241]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}