{"id":"W4417093832","doi":"10.1007/s11554-025-01816-6","title":"PRepDETR: a real-time detection transformer with partial convolutions and efficient cross-scale feature fusion","year":2025,"lang":"en","type":"article","venue":"Journal of Real-Time Image Processing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Object detection; Computation; Convolution (computer science); Feature extraction; Weighting; Feature (linguistics); Minimum bounding box; Pascal (unit); Fusion","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003364559,0.0002047524,0.0002984353,0.0002206184,0.0005912574,0.000385632,0.0003533294,0.000095937,0.000007606682],"category_scores_gemma":[0.00002962528,0.0001594417,0.00008122047,0.0009300925,0.0002083677,0.001039737,0.0000528002,0.0003407493,0.000007260619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001135814,"about_ca_system_score_gemma":0.0002202942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004873393,"about_ca_topic_score_gemma":0.000002795785,"domain_scores_codex":[0.9984627,0.00005840988,0.0004420622,0.0003621796,0.0003464735,0.0003282181],"domain_scores_gemma":[0.9985399,0.0001034884,0.0004442543,0.0002616857,0.0005020673,0.0001486063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002182882,0.0001411955,0.0002592455,0.00009506103,0.00002630251,0.00002065414,0.0004644304,0.00360857,0.909408,0.00005375234,0.0003719432,0.08533261],"study_design_scores_gemma":[0.003260735,0.0006734792,0.01265496,0.001237144,0.0002349531,0.001536893,0.00008871002,0.6753891,0.3000012,0.001605449,0.002605422,0.0007119472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2278853,0.0003011673,0.7683107,0.001167254,0.00006685441,0.0002778611,0.000002967739,0.0001184615,0.001869385],"genre_scores_gemma":[0.724453,0.0003622028,0.2728218,0.000110327,0.0002068027,0.00003274211,0.000002922171,0.00003411723,0.001976154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6717806,"threshold_uncertainty_score":0.6501845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005182249866145906,"score_gpt":0.2678167437060388,"score_spread":0.2626344938398929,"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."}}