{"id":"W2896492166","doi":"10.1109/mmsp.2018.8547080","title":"CPNet: A Context Preserver Convolutional Neural Network for Detecting Shadows in Single RGB Images","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Shadow (psychology); Artificial intelligence; Computer science; Convolutional neural network; RGB color model; Exploit; Computer vision; Context (archaeology); Segmentation; Deep learning; Task (project management); Pixel; Image (mathematics); Pattern recognition (psychology); Geography","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":[0.0003790008,0.00129188,0.0006339716,0.0009078606,0.0003271764,0.000461079,0.001586083,0.0006697372,0.001781487],"category_scores_gemma":[0.0007723969,0.0003736292,0.0004609127,0.000669302,0.0003211468,0.0009107813,0.0007632239,0.00103457,0.000816782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007858445,"about_ca_system_score_gemma":0.0009913613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01649058,"about_ca_topic_score_gemma":0.02931562,"domain_scores_codex":[0.9997391,0.00002337664,0.000008995298,0.0001095707,0.00007079367,0.00004821658],"domain_scores_gemma":[0.9997974,0.00003504869,0.00002705665,0.00005298956,0.0000690649,0.00001853033],"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":[0.0005809211,0.0003700941,0.004021166,0.0002696532,0.0002627294,0.000261249,0.00006131159,0.08345281,0.06792899,0.00229637,0.02440823,0.8160864],"study_design_scores_gemma":[0.00002659783,0.0001046795,0.003262752,0.00002727489,0.0000504486,0.0001760001,0.0000151063,0.9589363,0.0305664,0.00146797,0.005346515,0.00001990111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1978466,0.004734297,0.7608372,0.0004517117,0.0005704216,0.000331937,0.004068418,0.02187658,0.00928287],"genre_scores_gemma":[0.6372999,0.001644824,0.3376123,0.0004694155,0.0001500963,0.0001807885,0.0102111,0.0005470124,0.01188453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01649058,"threshold_uncertainty_score":0.03278917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06932561310747279,"score_gpt":0.3186075063649575,"score_spread":0.2492818932574848,"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."}}