{"id":"W4323527314","doi":"10.23977/jaip.2023.060105","title":"A survey of Few-Shot Action Recognition","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature (linguistics); Computer science; Shot (pellet); Action (physics); Field (mathematics); Artificial intelligence; Metric (unit); Process (computing); Embedding; Machine learning; One shot; Pattern recognition (psychology); Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003467983,0.00009989226,0.0002009691,0.0004689283,0.0001108515,0.0001484839,0.0003675878,0.00007667393,0.0001047399],"category_scores_gemma":[0.003643406,0.00009469289,0.0001044836,0.001362905,0.00004268789,0.002750828,0.00005506999,0.0003295345,0.0005866137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004470703,"about_ca_system_score_gemma":0.0001540711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001364428,"about_ca_topic_score_gemma":0.00007499721,"domain_scores_codex":[0.9978518,0.0004534067,0.0008504444,0.0001621272,0.0005029078,0.0001792812],"domain_scores_gemma":[0.9954189,0.001388791,0.001210187,0.0001860045,0.001708881,0.00008722297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002507329,0.0003257207,0.00006084528,0.00002208174,0.00007075313,0.00005753277,0.001025606,0.0003104813,0.01090185,0.001325875,0.001305926,0.9843426],"study_design_scores_gemma":[0.00027116,0.002533929,0.01347481,0.0004101633,0.0002203727,0.00104892,0.006514808,0.07958518,0.7810553,0.1027382,0.01131305,0.0008341235],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2791017,0.00007855151,0.7128727,0.002710155,0.003074805,0.0001760341,0.00001136042,0.0001010163,0.00187357],"genre_scores_gemma":[0.9930909,0.0004710765,0.005934919,0.0001895986,0.000245078,0.000002279428,0.000007640827,0.000009145393,0.0000493919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9835085,"threshold_uncertainty_score":0.7539928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3422828057942334,"score_gpt":0.4199338803764169,"score_spread":0.07765107458218351,"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."}}