{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005740874,0.0004165456,0.000410717,0.0005843842,0.001049154,0.001892627,0.0005632229,0.0001274412,0.001138592],"category_scores_gemma":[0.00001172727,0.0004231337,0.0001413941,0.0004832409,0.00006848735,0.004169824,0.0004730362,0.0007263793,0.0003497044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001499622,"about_ca_system_score_gemma":0.00007813508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007230943,"about_ca_topic_score_gemma":0.0001066344,"domain_scores_codex":[0.9967609,0.0005334122,0.0007470748,0.0007310477,0.0007740977,0.0004534365],"domain_scores_gemma":[0.998336,0.0002013833,0.0004786663,0.0004424578,0.0003094428,0.0002320404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006488046,0.0001542818,0.0001334897,0.00006187643,0.00003431235,0.0000270493,0.002654639,0.001140308,0.00004643824,0.0002025399,0.001166418,0.9943138],"study_design_scores_gemma":[0.001209337,0.001086711,0.001465959,0.0002674887,0.00002307645,0.0000777196,0.0007255315,0.9884707,0.0001221541,0.00410516,0.001811058,0.0006350805],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1346899,0.00005214618,0.8598157,0.001856775,0.002596478,0.0005475755,0.00003353546,0.0002595673,0.0001483812],"genre_scores_gemma":[0.9841875,0.0006142706,0.004664352,0.009306882,0.0001423013,0.0001822266,0.0008409816,0.00002537986,0.00003604186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9936787,"threshold_uncertainty_score":0.999822,"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."}}