{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008154569,0.0009558817,0.001038051,0.00103947,0.000322383,0.0007401966,0.001920027,0.001005311,0.003568016],"category_scores_gemma":[0.002155653,0.000374704,0.0009917425,0.0008398067,0.0005678385,0.001542886,0.001440103,0.001516526,0.001665501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008669677,"about_ca_system_score_gemma":0.0009244323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008869679,"about_ca_topic_score_gemma":0.01137526,"domain_scores_codex":[0.999521,0.00006154722,0.00001971269,0.0002156033,0.00009846574,0.00008372578],"domain_scores_gemma":[0.9993055,0.0002517078,0.00007996402,0.0001242386,0.0001496936,0.00008884988],"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":[0.0004885336,0.0003562285,0.003167378,0.0001652309,0.0001594631,0.0001490947,0.0001316194,0.08598215,0.06655645,0.006384401,0.009626645,0.8268329],"study_design_scores_gemma":[0.00001117487,0.0001056843,0.001782897,0.0000141149,0.00003350965,0.0001094416,0.00001711257,0.9819605,0.009270258,0.004807962,0.00186809,0.00001919609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03385566,0.001079942,0.9587137,0.0002103532,0.0001697327,0.0001027367,0.0003671919,0.003461399,0.002039207],"genre_scores_gemma":[0.7178084,0.0009443341,0.2654071,0.0007012093,0.0003727143,0.0003201787,0.002288179,0.0005637541,0.0115941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008869679,"threshold_uncertainty_score":0.01763612,"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."}}