{"id":"W2947220628","doi":"10.1016/j.image.2019.05.012","title":"A probabilistic topic model for event-based image classification and multi-label annotation","year":2019,"lang":"en","type":"article","venue":"Signal Processing Image Communication","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Annotation; Latent Dirichlet allocation; Computer science; Event (particle physics); Artificial intelligence; Convolutional neural network; Probabilistic logic; Automatic image annotation; Pattern recognition (psychology); Image (mathematics); Expectation–maximization algorithm; Topic model; Sketch; Image retrieval; Class (philosophy); Semantics (computer science); Mathematics; Maximum likelihood; Algorithm","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":[0.0004645506,0.0001595795,0.0001608396,0.0001050298,0.0002656663,0.0003435074,0.0006320069,0.00007288594,0.000002059935],"category_scores_gemma":[0.0001352484,0.0001584955,0.00003687931,0.0002691337,0.000105192,0.00197845,0.0001311493,0.0001616666,0.000007141641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008163023,"about_ca_system_score_gemma":0.0001518303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003067548,"about_ca_topic_score_gemma":0.000002061696,"domain_scores_codex":[0.9988335,0.00008881344,0.0003195786,0.0003872815,0.0001713768,0.0001994233],"domain_scores_gemma":[0.9982919,0.0001557796,0.0002743352,0.0006716195,0.0005552928,0.00005114331],"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":[0.00006309087,0.0003661087,0.0001552274,0.0006056983,0.000007272458,3.760266e-7,0.000901136,0.000445404,0.3309038,0.005481826,0.00007962892,0.6609905],"study_design_scores_gemma":[0.0007370326,0.00009158453,0.0003665138,0.0001261527,0.00001039552,0.000001536729,0.0000312815,0.9693304,0.01529692,0.01376547,0.00005456436,0.0001880966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003939651,0.0005253686,0.9933923,0.0008457697,0.00001207415,0.0009015416,0.000004648926,0.0002705002,0.0001081142],"genre_scores_gemma":[0.4772195,0.00001963646,0.5223649,0.0001233264,0.000005453703,0.0001148069,0.00003072851,0.0000113595,0.0001103191],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9688851,"threshold_uncertainty_score":0.6463258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.060258116452716,"score_gpt":0.3507502165690183,"score_spread":0.2904921001163023,"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."}}