{"id":"W4385261898","doi":"10.48550/arxiv.2307.12698","title":"MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Division of Mathematical Sciences; York University","keywords":"Computer science; Optical flow; Artificial intelligence; Embedding; Supervised learning; Encoder; Segmentation; Machine learning; Unsupervised learning; Motion (physics); Multimodal learning; Feature learning; Object (grammar); Joint (building); Focus (optics); Pattern recognition (psychology); Semi-supervised learning; Image (mathematics); Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001733502,0.001242652,0.00100194,0.0007621058,0.0004460721,0.0009413549,0.00331923,0.001727611,0.002034586],"category_scores_gemma":[0.00458778,0.0006226769,0.0008371985,0.0007764568,0.001007029,0.002189025,0.001901763,0.003046362,0.0009159803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008280953,"about_ca_system_score_gemma":0.00132426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005431277,"about_ca_topic_score_gemma":0.008827156,"domain_scores_codex":[0.9993359,0.000184423,0.00002432006,0.0002540074,0.0001379896,0.00006333733],"domain_scores_gemma":[0.9984002,0.0006638814,0.0001256813,0.0003573986,0.0003638427,0.00008906057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003269072,0.0005151819,0.002341422,0.0001707581,0.0002481693,0.000115618,0.0001593333,0.5379917,0.01291363,0.01294465,0.01025211,0.4220206],"study_design_scores_gemma":[0.000004754065,0.00002608915,0.0001032518,0.000003607577,0.000005172368,0.000009397289,0.000002701146,0.9961359,0.001082489,0.002293692,0.0003291912,0.000003800808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02216228,0.0005173426,0.9707204,0.0002402812,0.00007815861,0.0001040414,0.0001701981,0.004241055,0.001766279],"genre_scores_gemma":[0.5551693,0.0004249975,0.4324404,0.000633784,0.0001891005,0.0004115291,0.001864919,0.0005480713,0.00831795],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005431277,"threshold_uncertainty_score":0.01079929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09058569629909079,"score_gpt":0.2210678516634994,"score_spread":0.1304821553644086,"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."}}