{"id":"W2989035356","doi":"10.1109/iccv.2019.00403","title":"DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Differentiable function; Convolutional neural network; Matching (statistics); Artificial intelligence; Object (grammar); Segmentation; Deep learning; Artificial neural network; Gradient descent; Algorithm; Pattern recognition (psychology); Computer vision; Mathematics","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":[0.0001177413,0.0001334056,0.0001439728,0.00003497273,0.0001716426,0.0001480234,0.0005288101,0.00003408811,0.00006099772],"category_scores_gemma":[0.000005051413,0.0001196176,0.00006529682,0.0003290754,0.000009948819,0.0006468483,0.000165277,0.00008280607,0.000194094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000425096,"about_ca_system_score_gemma":0.00001936965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001110843,"about_ca_topic_score_gemma":0.00001709306,"domain_scores_codex":[0.9988163,0.0000245263,0.0002102661,0.0004268885,0.0001615029,0.0003605183],"domain_scores_gemma":[0.9989797,0.0002756412,0.0001057846,0.0005330293,0.00004178094,0.00006402275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002839075,0.0001068194,0.004094206,0.0000714796,0.00005844747,0.000001054994,0.0004727293,0.2345489,0.02335388,0.6681589,0.02637842,0.04272677],"study_design_scores_gemma":[0.001206762,0.0001797026,0.002329235,0.00004782889,0.00001916925,0.00001028892,0.00007464002,0.6449868,0.01094935,0.3066092,0.03293691,0.0006501229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02243659,0.00005265737,0.9732101,0.0004372296,0.0003746779,0.0008616017,0.000001848051,0.0002980711,0.002327203],"genre_scores_gemma":[0.4004705,0.00001031208,0.5930927,0.001336961,0.0002315365,0.0002441989,0.00002138656,0.00002133411,0.004570988],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.410438,"threshold_uncertainty_score":0.4877864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01284999507981074,"score_gpt":0.2610965531051605,"score_spread":0.2482465580253498,"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."}}