{"id":"W4312906857","doi":"10.1109/cvpr52688.2022.01361","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Toronto Metropolitan University; Vector Institute; York University","funders":"York University","keywords":"Computer science; Representation (politics); ENCODE; Artificial intelligence; Segmentation; Action (physics); Object (grammar); Code (set theory); Dynamic programming; Key (lock); Machine learning; Computer vision; Pattern recognition (psychology); Algorithm; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001330936,0.0008438625,0.0005893267,0.0006176414,0.0002886133,0.001646851,0.0007485963,0.0008715633,0.001818176],"category_scores_gemma":[0.008712027,0.0005112611,0.0004156275,0.001028206,0.0007792246,0.006057187,0.0009332809,0.001785138,0.0004219788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009867413,"about_ca_system_score_gemma":0.000596598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004265985,"about_ca_topic_score_gemma":0.005396356,"domain_scores_codex":[0.9996141,0.0001103636,0.0000227973,0.00009972887,0.00008135233,0.00007166136],"domain_scores_gemma":[0.9978495,0.001003736,0.0003158651,0.0004458138,0.0002938856,0.00009121899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000502026,0.0001587948,0.03637856,0.0003074808,0.0002994251,0.0002238272,0.000697739,0.5724989,0.05376191,0.08747143,0.005196251,0.2425037],"study_design_scores_gemma":[0.00000752089,0.00008086606,0.007150268,0.00004489822,0.00004822147,0.00007697396,0.00009190183,0.9074164,0.007345839,0.07629493,0.001413994,0.00002823608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3307317,0.001117214,0.6554507,0.004043208,0.0001177194,0.00004121243,0.001687668,0.0007506724,0.006059881],"genre_scores_gemma":[0.9683672,0.0006016477,0.02846792,0.0002507177,0.0000492113,0.00002282979,0.0006062649,0.0001121208,0.001522065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004265985,"threshold_uncertainty_score":0.008482337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03171531342754412,"score_gpt":0.2764183902390483,"score_spread":0.2447030768115042,"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."}}