{"id":"W2995034704","doi":"10.3390/signals2030037","title":"HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN","year":2021,"lang":"en","type":"preprint","venue":"Signals","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hallucinating; Computer science; Convolutional neural network; Task (project management); Artificial intelligence; Action (physics); Codebase; Resource (disambiguation); Machine learning; Source code","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":[0.0002591625,0.000920596,0.0003864897,0.0003560403,0.0001529511,0.0006063458,0.0007696266,0.0006483294,0.002905175],"category_scores_gemma":[0.001230613,0.0003301168,0.0007484797,0.0004127153,0.0003819739,0.001016247,0.001203775,0.0008271667,0.0008181655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003978238,"about_ca_system_score_gemma":0.0004283234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003424451,"about_ca_topic_score_gemma":0.004794641,"domain_scores_codex":[0.9998462,0.00002083591,0.00000681968,0.00006063384,0.00003455487,0.00003088341],"domain_scores_gemma":[0.9997613,0.00006046412,0.00003071068,0.00006985303,0.00004327985,0.00003434988],"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":[0.000487024,0.0001757655,0.00359487,0.0002563948,0.0001488691,0.0006096617,0.0002201438,0.3518775,0.1174286,0.008200066,0.009010294,0.5079907],"study_design_scores_gemma":[0.000007635826,0.00007449407,0.0006642953,0.000009831488,0.00001226697,0.0001015405,0.00002910891,0.9812198,0.01294061,0.003235869,0.001694462,0.00001003626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05866307,0.0002747581,0.9341748,0.000314041,0.0001463668,0.0000729555,0.0006196264,0.002569331,0.003165035],"genre_scores_gemma":[0.7527884,0.0005001352,0.2375541,0.0003642647,0.00008436265,0.0001086163,0.001939731,0.0002290286,0.006431436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003424451,"threshold_uncertainty_score":0.009718835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09175369972441666,"score_gpt":0.3376777254979606,"score_spread":0.2459240257735439,"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."}}