{"id":"W4385804921","doi":"10.1109/cvprw59228.2023.00248","title":"CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Microsoft","keywords":"Computer science; Baseline (sea); Artificial intelligence; Task (project management); Regularization (linguistics); Segmentation; Machine learning; Object (grammar); Semi-supervised learning; Supervised learning; Online learning; Learning object; Labeled data; Multimedia; Artificial neural network","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":[0.001597432,0.002489574,0.001350112,0.002842453,0.001379561,0.001924931,0.00434385,0.003078614,0.005967245],"category_scores_gemma":[0.006394813,0.0006589128,0.001619253,0.003090535,0.001076225,0.002534314,0.002564297,0.002864973,0.00593515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001853458,"about_ca_system_score_gemma":0.002185411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02948505,"about_ca_topic_score_gemma":0.06329369,"domain_scores_codex":[0.9982947,0.0002130282,0.0001421921,0.000727347,0.0004252019,0.0001975976],"domain_scores_gemma":[0.997712,0.0004044727,0.0002069719,0.0008868913,0.0005359405,0.0002536957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001432364,0.00122901,0.009374894,0.00262622,0.0004292872,0.0006663667,0.0003867898,0.02611306,0.02090711,0.005530879,0.6409753,0.2903286],"study_design_scores_gemma":[0.0007890541,0.001371438,0.03925956,0.0009571643,0.0002465446,0.002712199,0.001318373,0.3983701,0.0400128,0.02267188,0.4918115,0.0004793945],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1739674,0.00863639,0.1377029,0.002610998,0.002445511,0.003279528,0.5775216,0.06967902,0.02415664],"genre_scores_gemma":[0.09622756,0.0007949927,0.1073157,0.000562129,0.0001928819,0.0009690587,0.787419,0.001170018,0.005348633],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02948505,"threshold_uncertainty_score":0.05862683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0337194242945671,"score_gpt":0.3134656545191359,"score_spread":0.2797462302245688,"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."}}