{"id":"W4410351582","doi":"10.1016/j.eswa.2025.128127","title":"High performance point-Voxel feature set abstraction with mamba for 3D object detection","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Jilin Province Key R&D Plan Project; Education Department of Jilin Province; Ministry of Education; National Natural Science Foundation of China; Jiangsu University; Jilin Province Development and Reform Commission; Ontario Ministry of Natural Resources and Forestry","keywords":"Abstraction; Computer science; Feature (linguistics); Object (grammar); Set (abstract data type); Artificial intelligence; Point (geometry); Voxel; Pattern recognition (psychology); Computer vision; Mathematics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004143785,0.0009625779,0.001267445,0.0008026406,0.0004774086,0.0009799822,0.002140774,0.0008476579,0.01095791],"category_scores_gemma":[0.001547716,0.0006530125,0.0008854531,0.001262105,0.0002702634,0.001164062,0.001747375,0.001416612,0.003734031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005446855,"about_ca_system_score_gemma":0.001079802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00634605,"about_ca_topic_score_gemma":0.01116586,"domain_scores_codex":[0.9996505,0.00004173709,0.00001814126,0.00007436382,0.000163943,0.00005135659],"domain_scores_gemma":[0.9996744,0.00009334772,0.00002057702,0.00009019564,0.00009969504,0.00002161609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006737541,0.0001461031,0.001165329,0.0003006504,0.0002489505,0.0001545595,0.0001155477,0.08921476,0.07155803,0.008278403,0.0163384,0.8118054],"study_design_scores_gemma":[0.00002205862,0.00005702804,0.0005719602,0.00001063625,0.00002375864,0.00007117427,0.00003161246,0.9712574,0.0173715,0.005966641,0.004598109,0.0000180203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006992925,0.0002163978,0.9829546,0.00006717622,0.00004395289,0.00004096774,0.0002452541,0.008569136,0.0008696932],"genre_scores_gemma":[0.1934471,0.0001954741,0.8015979,0.0001350734,0.00003877878,0.0001665563,0.001194732,0.0005694209,0.002654999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01095791,"threshold_uncertainty_score":0.03665781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008977726881029904,"score_gpt":0.2536343444885778,"score_spread":0.2446566176075479,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}