{"id":"https://openalex.org/W7123758562","doi":"https://doi.org/10.1109/mmsp64401.2025.11324346","title":"S-LAM3D: Segmentation-Guided Monocular 3D Object Detection via Feature Space Fusion","display_name":"S-LAM3D: Segmentation-Guided Monocular 3D Object Detection via Feature Space Fusion","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123758562","doi":"https://doi.org/10.1109/mmsp64401.2025.11324346"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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":null,"display_name":"Diana-Alexandra Sas","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Diana-Alexandra Sas","raw_affiliation_strings":["Technical University of Cluj-Napoca,Computer Science Department,Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Computer Science Department,Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061493057","display_name":"Florin Oniga","orcid":"https://orcid.org/0000-0003-4875-2220"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Florin Oniga","raw_affiliation_strings":["Technical University of Cluj-Napoca,Computer Science Department,Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Computer Science Department,Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":1.1828,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85995482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9438999891281128,"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":0.9438999891281128,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.005900000222027302,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.004699999932199717,"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/object-detection","display_name":"Object detection","score":0.6466000080108643},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5799999833106995},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5185999870300293},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5120000243186951},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49619999527931213},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.43860000371932983},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4180000126361847},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3873000144958496},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.38339999318122864}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8259000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695000171661377},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6790000200271606},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6466000080108643},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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":24,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2963323244","https://openalex.org/W2964309882","https://openalex.org/W2997790735","https://openalex.org/W3035180028","https://openalex.org/W3130463448","https://openalex.org/W3175515048","https://openalex.org/W3204439495","https://openalex.org/W3211620692","https://openalex.org/W4286285640","https://openalex.org/W4312865155","https://openalex.org/W4313149358","https://openalex.org/W4386075853","https://openalex.org/W4386453674","https://openalex.org/W4386939374","https://openalex.org/W4390873008","https://openalex.org/W4390874575","https://openalex.org/W4402727115","https://openalex.org/W4402727359","https://openalex.org/W4403183568","https://openalex.org/W4404295200","https://openalex.org/W4404612908","https://openalex.org/W4408423731","https://openalex.org/W4415798746"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,66,134],"Object":[2,135],"Detection":[3,136],"represents":[4],"a":[5,20,74],"challenging":[6],"Computer":[7],"Vision":[8],"task":[9],"due":[10],"to":[11],"the":[12,15,31,42,46,89,94,98,104,111,132,139,153,162,167],"nature":[13],"of":[14,113],"input":[16,47,163],"used,":[17],"which":[18],"is":[19,108,129],"single":[21],"2D":[22],"image,":[23],"lacking":[24],"in":[25,152],"any":[26],"depth":[27,32],"cues":[28],"and":[29,84,156,158],"placing":[30],"estimation":[33],"problem":[34],"as":[35,56],"an":[36],"ill-posed":[37],"one.":[38],"Existing":[39],"solutions":[40],"leverage":[41],"information":[43,82,116],"extracted":[44],"from":[45],"by":[48,61],"using":[49],"Convolutional":[50],"Neural":[51],"Networks":[52],"or":[53,101,172],"Transformer":[54],"architectures":[55],"feature":[57,90],"extraction":[58],"backbones,":[59],"followed":[60],"specific":[62],"detection":[63,99,119],"heads":[64],"for":[65,92,149,169],"parameters":[67],"prediction.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"introduce":[73],"decoupled":[75],"strategy":[76],"based":[77],"on":[78,109,117,131,145],"injecting":[79],"precomputed":[80],"segmentation":[81,115],"priors":[83],"fusing":[85],"them":[86],"directly":[87],"into":[88],"space":[91],"guiding":[93],"detection,":[95],"without":[96,121],"expanding":[97],"model":[100],"jointly":[102],"learning":[103],"priors.":[105],"The":[106,126],"focus":[107],"evaluating":[110],"impact":[112],"additional":[114,123,170],"existing":[118],"pipelines":[120],"adding":[122],"prediction":[124],"branches.":[125],"proposed":[127],"method":[128],"evaluated":[130],"KITTI":[133],"Benchmark,":[137],"outperforming":[138],"equivalent":[140],"architecture":[141],"that":[142,160],"relies":[143],"only":[144],"RGB":[146],"image":[147],"features":[148],"small":[150],"objects":[151],"scene:":[154],"pedestrians":[155],"cyclists,":[157],"proving":[159],"understanding":[161],"data":[164],"can":[165],"balance":[166],"need":[168],"sensors":[171],"training":[173],"data.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2026-01-14T00:00:00"}