{"id":"W2967858478","doi":"10.1109/3dv.2019.00072","title":"SIPs: Succinct Interest Points from Unsupervised Inlierness Probability Learning","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Succinctness; Detector; Computer science; Metric (unit); Point (geometry); Range (aeronautics); Code (set theory); Artificial intelligence; Interest point detection; Pixel; Pattern recognition (psychology); Machine learning; Algorithm; Theoretical computer science; Mathematics; Image (mathematics); Image processing; Feature detection (computer vision)","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":[0.0006088974,0.0005536415,0.0007289108,0.0001671881,0.0001018435,0.0005294259,0.00305129,0.0004653328,0.0001855477],"category_scores_gemma":[0.0005027642,0.0004817703,0.0002756164,0.000296675,0.00008474384,0.0008147073,0.006723604,0.001777064,0.0003022293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002279772,"about_ca_system_score_gemma":0.0002526437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004084122,"about_ca_topic_score_gemma":0.00003853343,"domain_scores_codex":[0.996429,0.000334524,0.000645307,0.001696013,0.0004104156,0.0004846981],"domain_scores_gemma":[0.9964554,0.0003738062,0.0003252128,0.002361171,0.0003233107,0.0001610714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002726849,0.001211726,0.0742633,0.001774334,0.0005350139,0.0002110136,0.004082181,0.002182547,0.005337428,0.04159422,0.003505899,0.8650296],"study_design_scores_gemma":[0.001338998,0.0005451684,0.02104506,0.001920529,0.00006652311,0.00001278646,0.0001310403,0.08839086,0.1281099,0.7333776,0.02186416,0.003197397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06529545,0.0003066129,0.9268544,0.0005560948,0.0007050883,0.0009228591,0.00001426684,0.001717884,0.00362734],"genre_scores_gemma":[0.751307,0.000160946,0.2468265,0.0003852038,0.0001453012,0.00006033713,0.00008145345,0.00004491216,0.0009883476],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8618323,"threshold_uncertainty_score":0.9997634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05372909799159704,"score_gpt":0.2971477280750073,"score_spread":0.2434186300834102,"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."}}