{"id":"W4381615915","doi":"10.1007/s11042-023-15845-5","title":"An improved dense-to-sparse cross-modal fusion network for 3D object detection in RGB-D images","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Computer science; RGB color model; Artificial intelligence; Computer vision; Context (archaeology); Object detection; Process (computing); Modal; Fuse (electrical); Sensor fusion; Object (grammar); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001096606,0.00102018,0.001051741,0.0008240545,0.0005433544,0.0006955757,0.001602177,0.001296292,0.002843983],"category_scores_gemma":[0.001382711,0.000605752,0.001013254,0.001001828,0.0004360346,0.001429402,0.002164385,0.001092087,0.00122404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005636998,"about_ca_system_score_gemma":0.0009939086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007227691,"about_ca_topic_score_gemma":0.01006652,"domain_scores_codex":[0.9993218,0.00009256998,0.000035462,0.0001808018,0.0002831653,0.00008612218],"domain_scores_gemma":[0.9995097,0.000108869,0.0000334029,0.00006354335,0.0002569849,0.00002749734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004167837,0.0002432153,0.0009929108,0.0001544077,0.0001990857,0.0001053345,0.0000943195,0.123152,0.06316712,0.003656468,0.005608882,0.8022096],"study_design_scores_gemma":[0.000008072902,0.00005571005,0.0003831945,0.000007214728,0.00003174362,0.00005610159,0.000009796565,0.9894852,0.008190233,0.0009683758,0.00079085,0.00001339916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01234939,0.0003947061,0.984858,0.0001174698,0.00008088737,0.00005251843,0.0001087239,0.001004241,0.00103396],"genre_scores_gemma":[0.3149476,0.0006382075,0.6764069,0.0005104279,0.0001451385,0.0002301902,0.0007837141,0.0001408688,0.006196952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007227691,"threshold_uncertainty_score":0.01437122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02465154492700231,"score_gpt":0.312014989238469,"score_spread":0.2873634443114667,"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."}}