{"id":"W2995680717","doi":"10.48550/arxiv.1912.08936","title":"One-Shot Weakly Supervised Video Object Segmentation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Computer vision; Object (grammar); Pascal (unit); Scale-space segmentation; Segmentation-based object categorization; Shot (pellet); Bounding overwatch; Image segmentation; Benchmark (surveying); Pattern recognition (psychology); Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034505,0.001462643,0.001536028,0.001168196,0.0005665983,0.001195075,0.002605233,0.001931972,0.002936981],"category_scores_gemma":[0.003135826,0.0005707804,0.001153546,0.0007967565,0.001012141,0.001884312,0.001706462,0.001480244,0.002361735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009313902,"about_ca_system_score_gemma":0.001076888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004025566,"about_ca_topic_score_gemma":0.008934479,"domain_scores_codex":[0.9988766,0.0001346039,0.00004108578,0.0006225124,0.0001917002,0.0001334931],"domain_scores_gemma":[0.9986311,0.0003326577,0.000126299,0.000450673,0.0003428235,0.0001164409],"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":[0.001455812,0.0005453983,0.004938575,0.0006638386,0.0002388545,0.0003388063,0.0003254778,0.101697,0.1286533,0.005059415,0.01960687,0.7364767],"study_design_scores_gemma":[0.00002585724,0.0002060991,0.003256946,0.0000397863,0.0000374039,0.0002361422,0.0001002652,0.9428611,0.04168528,0.006908893,0.004608092,0.00003403375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1058892,0.0009701477,0.8733404,0.0002384142,0.0001777426,0.0003120717,0.001760914,0.01229792,0.005013101],"genre_scores_gemma":[0.5751081,0.0003732275,0.4012334,0.000416072,0.0001477469,0.0003144272,0.011216,0.001091096,0.01009991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004025566,"threshold_uncertainty_score":0.00982523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1295918646190955,"score_gpt":0.2171104395152478,"score_spread":0.08751857489615225,"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."}}