{"id":"W2972833696","doi":"10.3390/sym11091155","title":"Low-Rank Multi-Channel Features for Robust Visual Object Tracking","year":2019,"lang":"en","type":"article","venue":"Symmetry","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Computer science; Support vector machine; Kernel (algebra); Histogram; Computational complexity theory; Video tracking; Computer vision; Eye tracking; Local binary patterns; Circulant matrix; Histogram of oriented gradients; Mathematics; Algorithm; Object (grammar); Image (mathematics)","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":[0.001016804,0.0002226468,0.000319681,0.0001876398,0.0001433544,0.0002273564,0.0007070708,0.0001500406,0.000008637203],"category_scores_gemma":[0.0002221804,0.000200923,0.0002095597,0.000479082,0.0000258443,0.000465559,0.0001388086,0.0002338063,0.00009540136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003814405,"about_ca_system_score_gemma":0.00006381142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002539007,"about_ca_topic_score_gemma":0.00001932603,"domain_scores_codex":[0.9982448,0.0001263564,0.0002441114,0.0006054576,0.0002668493,0.000512386],"domain_scores_gemma":[0.9986046,0.0005172148,0.0001121622,0.0005464606,0.0001259445,0.00009363682],"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":[0.0002090815,0.001286171,0.03077449,0.001159685,0.0004555232,0.00008671611,0.003591942,0.01090138,0.01633793,0.02109523,0.00543788,0.908664],"study_design_scores_gemma":[0.009757078,0.001318966,0.340247,0.00062081,0.00006328603,0.0001698752,0.0005899349,0.4780861,0.1519523,0.008717995,0.00540765,0.00306893],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0405241,0.0004454571,0.9549967,0.0002369135,0.002253088,0.0004408129,0.00000735641,0.0003023713,0.0007931991],"genre_scores_gemma":[0.8401405,0.00001123258,0.1584058,0.0004810039,0.0002346966,0.00002175148,0.000006630177,0.00002910323,0.0006691953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9055951,"threshold_uncertainty_score":0.8193402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03141101484369791,"score_gpt":0.3134567235244978,"score_spread":0.2820457086807999,"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."}}