{"id":"W2043472121","doi":"10.1109/crv.2014.24","title":"Segmenting Objects in Weakly Labeled Videos","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Artificial intelligence; Computer science; Object (grammar); Computer vision; Frame (networking); Market segmentation; Video tracking; Segmentation; Class (philosophy); Pattern recognition (psychology)","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":[0.000358794,0.00009097892,0.0001218481,0.000104532,0.00004309779,0.00008114184,0.0004627263,0.00003589722,0.0000148285],"category_scores_gemma":[0.0001574884,0.00007888243,0.00002849022,0.0004272292,0.00001418181,0.0006504665,0.0002159541,0.0001035557,0.00005549451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002548678,"about_ca_system_score_gemma":0.00001642691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002441858,"about_ca_topic_score_gemma":0.00001954323,"domain_scores_codex":[0.9991131,0.00004784119,0.0001734849,0.0002697045,0.0001438628,0.0002520119],"domain_scores_gemma":[0.999419,0.0001001818,0.00004479164,0.0003535078,0.00003699469,0.00004552553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007003224,0.0001112056,0.005912251,0.00003246842,0.000007278516,0.00002616172,0.0005450904,0.00001912048,0.102026,0.1503638,0.001209523,0.73974],"study_design_scores_gemma":[0.0005182272,0.0001703458,0.003387895,0.00006833955,0.000001912715,0.000007942087,0.00003144223,0.03714506,0.9019875,0.04400595,0.01228823,0.0003871387],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006987743,0.00003831425,0.9649984,0.0002330672,0.00006074407,0.0001057557,7.01455e-8,0.0004549165,0.02712102],"genre_scores_gemma":[0.7377757,0.00001190827,0.2605991,0.0007906857,0.00002721373,0.000008306899,3.044769e-7,0.000005606987,0.0007811958],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7999614,"threshold_uncertainty_score":0.3216732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004956278421576463,"score_gpt":0.2334042608007185,"score_spread":0.228447982379142,"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."}}