{"id":"W4372260475","doi":"10.1109/icassp49357.2023.10096811","title":"Temporal Contrastive Learning with Curriculum","year":2023,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; CLIPS; Artificial intelligence; Context (archaeology); Task (project management); Sampling (signal processing); Representation (politics); Natural language processing; Feature learning; Machine learning; Speech recognition; Pattern recognition (psychology); Computer vision","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":[0.001065508,0.0009783738,0.0008234395,0.0007228667,0.0004098038,0.0006446415,0.002092868,0.001072615,0.003378166],"category_scores_gemma":[0.005283173,0.0003767388,0.0006224271,0.0007431273,0.0007162614,0.001900945,0.00181928,0.002269854,0.0008077841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007905185,"about_ca_system_score_gemma":0.0009843662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002706673,"about_ca_topic_score_gemma":0.004468713,"domain_scores_codex":[0.9994181,0.0001442815,0.00002362513,0.0002184216,0.000122854,0.00007271599],"domain_scores_gemma":[0.9985598,0.0006846768,0.0001389258,0.0002659369,0.0002131734,0.0001375599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004944954,0.0006340604,0.003513219,0.0001685641,0.00008931154,0.0001411464,0.0001749446,0.1566698,0.03064677,0.01425437,0.007597565,0.7856157],"study_design_scores_gemma":[0.00003898481,0.0002086244,0.0003790717,0.00001229819,0.00001632722,0.00006551586,0.00001735982,0.9857248,0.006374978,0.005518357,0.001632278,0.00001131402],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03333442,0.0003733294,0.9619116,0.0002238606,0.00006773341,0.0001054159,0.00009986226,0.001611749,0.002271966],"genre_scores_gemma":[0.5966817,0.0003003849,0.3954064,0.0006999265,0.000151494,0.0003681657,0.0007410319,0.0002829827,0.005367904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003378166,"threshold_uncertainty_score":0.01130104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01004706294568774,"score_gpt":0.2270174527637986,"score_spread":0.2169703898181109,"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."}}