{"id":"W3138766416","doi":"10.48550/arxiv.2103.10567","title":"CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Softmax function; Computer science; Artificial intelligence; Pattern recognition (psychology); Action recognition; Shot (pellet); Classifier (UML); Gaussian; Mixture model; Speech recognition; Deep learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001955572,0.0002494924,0.0002609013,0.0002759054,0.0002675079,0.0002905796,0.0002951164,0.0003013008,0.00003723974],"category_scores_gemma":[0.00003418873,0.0003145445,0.0002256203,0.0002337393,0.00005514473,0.0008039092,0.0002502001,0.0003337566,0.00002754754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001574824,"about_ca_system_score_gemma":0.0001048815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008981375,"about_ca_topic_score_gemma":0.000123747,"domain_scores_codex":[0.9983594,0.0001368598,0.0002165304,0.0009621671,0.00008799489,0.000237046],"domain_scores_gemma":[0.9986863,0.00008751344,0.0003108295,0.0004010634,0.0003944303,0.0001199158],"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":[0.004008979,0.00872926,0.07117052,0.01129009,0.004609447,0.002520974,0.002838741,0.03869116,0.03816468,0.06320772,0.01192478,0.7428436],"study_design_scores_gemma":[0.006096048,0.0004670972,0.01398336,0.001025872,0.0005367402,0.0000280304,0.0008340881,0.9223367,0.008547301,0.04237222,0.001938516,0.001834044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5456051,0.00001830848,0.4528933,0.00009348273,0.0006665298,0.0003487436,0.00002920807,0.000139852,0.0002055097],"genre_scores_gemma":[0.9963006,0.0001177132,0.002080487,0.0001742711,0.0001220471,0.000008478084,0.0006207415,0.00001638375,0.0005592934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8836455,"threshold_uncertainty_score":0.9999307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2507099366280788,"score_gpt":0.2325650825515762,"score_spread":0.01814485407650263,"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."}}