{"id":"W2087852087","doi":"10.1117/12.477185","title":"Video object segmentation in the cellular neural networks architecture","year":2002,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Cellular Automata and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute of Steel Construction; National Science Foundation","keywords":"Computer science; Artificial intelligence; Segmentation; Computer vision; Image segmentation; Video tracking; Key (lock); Object (grammar); Cellular neural network; Scale-space segmentation; Segmentation-based object categorization; Artificial neural network; Interactivity; Pattern recognition (psychology); Multimedia","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0000896536,0.0001685802,0.0001768512,0.0001572225,0.000255347,0.0003373271,0.0003449226,0.000476611,0.0009788353],"category_scores_gemma":[0.0003334803,0.0001228423,0.0001751681,0.0002087742,0.0002932887,0.0003977593,0.0001736734,0.0002156209,0.0001504743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008567435,"about_ca_system_score_gemma":0.0004817576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01021042,"about_ca_topic_score_gemma":0.008049787,"domain_scores_codex":[0.9999529,0.000008881706,0.0000019982,0.00001595954,0.00001138886,0.00000874636],"domain_scores_gemma":[0.9999458,0.00001597865,0.000005811418,0.000006501878,0.00002110584,0.000004802046],"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":[0.00008789513,0.0000250654,0.0007293065,0.00004292913,0.00001514228,0.000102179,0.00005412574,0.88722,0.03145842,0.0435652,0.0008964739,0.03580333],"study_design_scores_gemma":[0.000003037999,0.00001116352,0.0001379953,0.000001974738,0.000002966724,0.00001093079,0.000003733745,0.9931758,0.002833028,0.003216614,0.0006002444,0.000002545392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2724732,0.0006839429,0.7118393,0.0005089704,0.0001349342,0.00004813238,0.0001251279,0.0008921794,0.01329412],"genre_scores_gemma":[0.9000238,0.0002568135,0.09336337,0.00007407842,0.00001608265,0.00006456054,0.00008401568,0.00002775568,0.006089557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01021042,"threshold_uncertainty_score":0.020302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051177317546601,"score_gpt":0.2139957431944918,"score_spread":0.2034839700190258,"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."}}