{"id":"W2963814513","doi":"10.1609/aaai.v33i01.33018545","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":344,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence; Representation (politics); Task (project management); Relation (database); Pattern recognition (psychology); Feature learning; Inpainting; Deep learning; Domain (mathematical analysis); Space (punctuation); Machine learning; Image (mathematics); Computer vision; Mathematics; Data mining","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000299099,0.0001859014,0.0002181452,0.000145838,0.0001917814,0.0003406111,0.0009028995,0.00007034081,0.0002776748],"category_scores_gemma":[0.0001334581,0.0001347935,0.0000854717,0.0006139651,0.00008329297,0.0008555981,0.000168404,0.0002993454,0.001021557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003951635,"about_ca_system_score_gemma":0.00007253692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001824608,"about_ca_topic_score_gemma":0.000002771148,"domain_scores_codex":[0.9983978,0.00002885229,0.000338884,0.0004865485,0.0004868073,0.0002610538],"domain_scores_gemma":[0.9986709,0.0001088922,0.0003373414,0.0002441706,0.0005717635,0.00006693818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001622091,0.0003488319,0.002564398,0.000149136,0.00007731983,0.000001542214,0.005339805,0.0004529482,0.2695869,0.6061917,0.0002233005,0.1149019],"study_design_scores_gemma":[0.00007304839,0.0003800163,0.0002759741,0.0002610341,0.00001928335,0.000008438049,0.0007683164,0.2391263,0.7280321,0.03048408,0.0002955124,0.0002759502],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.944809,0.00001015415,0.01074325,0.00271235,0.0002916981,0.0006985455,0.000001245396,0.0003182252,0.04041557],"genre_scores_gemma":[0.9939499,0.00002492248,0.004562963,0.0001033029,0.00004885393,0.00002009356,0.000001072522,0.00001288101,0.001275965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5757076,"threshold_uncertainty_score":0.9997563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03845464712294914,"score_gpt":0.2635565649297661,"score_spread":0.225101917806817,"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."}}