{"id":"W4416371861","doi":"10.2316/j.2026.206-1259","title":"EXTENDED DEEP DOWNSAMPLING NETWORK WITH MULTI-INTERACTIVE REFINEMENT FOR UNDERWATER SALIENT OBJECT DETECTION. 280-294","year":2025,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Underwater Vehicles and Communication Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Upsampling; Object detection; Object (grammar); Salient; Pattern recognition (psychology); Underwater; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0006218553,0.0008693173,0.0008734796,0.0007417444,0.0003095359,0.0005005064,0.001216995,0.0005848018,0.003484182],"category_scores_gemma":[0.001264518,0.0005302199,0.0007868542,0.000640908,0.0002985468,0.0009053784,0.001137997,0.0008367726,0.001009683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000385466,"about_ca_system_score_gemma":0.0007683801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00980383,"about_ca_topic_score_gemma":0.01747698,"domain_scores_codex":[0.9997305,0.00005285611,0.00001183646,0.00006226415,0.00009272688,0.00004979797],"domain_scores_gemma":[0.9996965,0.0001046049,0.00002267178,0.0000528779,0.0001034596,0.00001999095],"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":[0.0003620606,0.0001558815,0.001450736,0.0001453345,0.000158325,0.0001783877,0.0001370192,0.1768702,0.03937966,0.00563409,0.00997851,0.7655498],"study_design_scores_gemma":[0.000007385429,0.00003064567,0.0003756301,0.000006547235,0.00001839523,0.00004235431,0.00001483673,0.9916877,0.004989957,0.001439689,0.001379246,0.000007506549],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0189578,0.0004934479,0.9769669,0.0001249823,0.00008159189,0.00004364085,0.0001778216,0.001061455,0.002092287],"genre_scores_gemma":[0.3709278,0.0006868271,0.6148503,0.0002522797,0.0001247251,0.0001266084,0.001595348,0.0004056464,0.01103037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00980383,"threshold_uncertainty_score":0.01949352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177985220646726,"score_gpt":0.2585860917002281,"score_spread":0.2468062394937608,"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."}}