{"id":"W4392033629","doi":"10.32920/25266739.v1","title":"Video Action Recognition Using Depth Motion Maps","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Motion (physics); Metric (unit); Feature (linguistics); Noise (video); Representation (politics); Action (physics); Pyramid (geometry); Quarter-pixel motion; Pattern recognition (psychology); Image (mathematics); Mathematics; Engineering","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002888478,0.0002779828,0.000210366,0.0004944078,0.0001459317,0.0008324037,0.0003408747,0.0003616,0.0002201259],"category_scores_gemma":[0.00002491278,0.0002799513,0.0002053973,0.0002803466,0.00001946376,0.000555659,0.0008224668,0.0007911162,0.001830465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002618896,"about_ca_system_score_gemma":0.0001234345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001506698,"about_ca_topic_score_gemma":0.0000773482,"domain_scores_codex":[0.9981099,0.0001091734,0.000376214,0.0008257421,0.0003345256,0.0002444451],"domain_scores_gemma":[0.9990346,0.00003835118,0.0001790447,0.0004771183,0.0001812674,0.00008961119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006534583,0.000089817,0.00001058585,0.0004328667,0.0000836051,0.00002623336,0.0002908148,0.000359721,0.00194648,0.002074297,0.004959381,0.9897197],"study_design_scores_gemma":[0.0002428294,0.00004731932,0.0001861724,0.0007358792,0.0001369053,0.0001266862,0.00009406565,0.306226,0.02633561,0.6627319,0.002319626,0.0008169903],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08336864,0.0001199605,0.8850217,0.0005770681,0.006475187,0.0004532997,0.00002777833,0.001449303,0.02250708],"genre_scores_gemma":[0.9211434,0.000178983,0.07443368,0.0005840389,0.001596462,0.00009056502,0.0005182372,0.00005988133,0.001394724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9889027,"threshold_uncertainty_score":0.9999653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.130921422579896,"score_gpt":0.3246563746924735,"score_spread":0.1937349521125775,"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."}}