{"id":"W2054534213","doi":"10.1109/cvpr.2011.5995649","title":"Learning better image representations using ‘flobject analysis’","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Latent Dirichlet allocation; Artificial intelligence; Pyramid (geometry); Generalization; Optical flow; Pattern recognition (psychology); Image (mathematics); Probabilistic logic; Matching (statistics); Topic model; Unsupervised learning; Representation (politics); Computer vision; Machine learning; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003579077,0.0002148033,0.0002942298,0.0004847163,0.0002807549,0.0001974282,0.0007451053,0.00007818868,0.0004787895],"category_scores_gemma":[0.0001829074,0.0001923674,0.0002558577,0.001862563,0.00009207346,0.002125169,0.0004139374,0.0002820647,0.0002499508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004836479,"about_ca_system_score_gemma":0.00003885597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003929956,"about_ca_topic_score_gemma":0.00005931545,"domain_scores_codex":[0.9981238,0.0001453748,0.0003756584,0.0006314253,0.0003090188,0.000414765],"domain_scores_gemma":[0.9983688,0.0001050342,0.0001730552,0.001033241,0.0002161082,0.0001037807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007226905,0.0006162106,0.1217682,0.00006366445,0.001797636,0.00002491118,0.01200474,0.0006605685,0.7780563,0.02488933,0.002353766,0.05769239],"study_design_scores_gemma":[0.001625695,0.0006961683,0.07759571,0.0001441439,0.002053343,0.0002757255,0.00070182,0.01977798,0.3451925,0.09433679,0.4520717,0.005528452],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01894478,0.00004048746,0.9635996,0.00009715134,0.00007315443,0.0001444018,0.000001363181,0.0007638347,0.01633527],"genre_scores_gemma":[0.03634995,0.00003160756,0.9603657,0.0003945252,0.00005719876,0.000009573752,0.00001023431,0.00001820203,0.002763021],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4497179,"threshold_uncertainty_score":0.7844517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08376107753801265,"score_gpt":0.3562386283027814,"score_spread":0.2724775507647687,"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."}}