{"id":"W4285163934","doi":"10.1109/tmm.2022.3187856","title":"C$^{2}$DFNet: Criss-Cross Dynamic Filter Network for RGB-D Salient Object Detection","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; RGB color model; Computer vision; Context (archaeology); Convolution (computer science); Modality (human–computer interaction); Filter (signal processing); Salient; Pattern recognition (psychology); Artificial neural network","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004752502,0.000248382,0.0002098128,0.0002600065,0.001449495,0.000161136,0.0005282966,0.00009112141,0.0002053777],"category_scores_gemma":[0.000009074944,0.000266864,0.0003161773,0.0007558559,0.00005489159,0.0003772013,0.000009978127,0.0004443435,0.0001065246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003028829,"about_ca_system_score_gemma":0.00005317909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000427129,"about_ca_topic_score_gemma":0.0001437481,"domain_scores_codex":[0.9977142,0.0001818145,0.0004063432,0.0006778214,0.0005018029,0.0005180828],"domain_scores_gemma":[0.9989162,0.0001837307,0.0001330845,0.0005195857,0.0001038564,0.0001435248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002575976,0.0007946005,0.00005056196,0.00003208118,0.0001087394,0.000009952877,0.001591127,0.4955871,0.01728534,0.00007587591,0.001052175,0.4831548],"study_design_scores_gemma":[0.001433659,0.0009361678,0.001156088,0.000009920763,0.00002995112,0.00003376758,0.0001095928,0.9710336,0.01827154,0.0005131671,0.006053708,0.0004188457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03441493,0.00002970696,0.9563072,0.0002360246,0.007697451,0.0006918993,0.00005176738,0.0005000873,0.00007095024],"genre_scores_gemma":[0.9859493,0.00001066398,0.01106457,0.0005241624,0.0001174131,0.0008977868,0.00001307255,0.00003594525,0.001387016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9515345,"threshold_uncertainty_score":0.9999784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01810113609284413,"score_gpt":0.2926798188489161,"score_spread":0.2745786827560719,"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."}}