{"id":"W2754041308","doi":"10.1007/978-3-319-67777-4_32","title":"Probabilistic Hypergraph Optimization for Salient Object Detection","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Hypergraph; Pairwise comparison; Salient; Probabilistic logic; Computer science; Graph; Representation (politics); Artificial intelligence; Similarity (geometry); Pattern recognition (psychology); Correlation; Spatial relation; Object (grammar); Theoretical computer science; Algorithm; Mathematics; Image (mathematics); Combinatorics","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"],"consensus_categories":[],"category_scores_codex":[0.0008909233,0.0004416933,0.000407128,0.0008546739,0.000807683,0.0008994327,0.002033491,0.0003271686,0.00001193078],"category_scores_gemma":[0.0002609118,0.0004146672,0.0002209,0.0002802052,0.0004287712,0.000777889,0.0004606129,0.0004034313,0.00001788314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003411073,"about_ca_system_score_gemma":0.0002921524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001776506,"about_ca_topic_score_gemma":0.0001416807,"domain_scores_codex":[0.996709,0.00003308465,0.0004948822,0.00150507,0.0007348998,0.0005229947],"domain_scores_gemma":[0.9974342,0.000189596,0.0004599161,0.001331482,0.0004448656,0.0001399218],"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":[0.0000135227,0.00003793005,0.000005774105,0.00006801265,0.000009908132,0.000006806723,0.0001950491,0.2643337,0.0002573024,0.00737397,0.000007301257,0.7276907],"study_design_scores_gemma":[0.00030421,0.0003800175,0.00004597912,0.0001694369,0.00001251192,0.00002954309,9.264577e-8,0.8906897,0.001518793,0.10572,0.0006554595,0.0004742969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006911344,0.00009029657,0.9930314,0.0002943854,0.004020841,0.000966974,0.000005140778,0.0002447476,0.00127712],"genre_scores_gemma":[0.5443412,0.00006662772,0.4524774,0.0008405026,0.0009153791,0.0001489306,0.00001913971,0.00008024259,0.001110579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7272164,"threshold_uncertainty_score":0.9998305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02147262446464387,"score_gpt":0.2677254693605094,"score_spread":0.2462528448958656,"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."}}