{"id":"W4292794024","doi":"10.1109/cvprw56347.2022.00055","title":"ActAR: Actor-Driven Pose Embeddings for Video Action Recognition","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Key (lock); Action (physics); Task (project management); Process (computing); Action recognition; Encoding (memory); Optical flow; Machine learning; Frame (networking); Pattern recognition (psychology); Human–computer interaction; Computer vision; Image (mathematics)","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","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006695304,0.0005931463,0.0005384645,0.0007026682,0.001392962,0.0009092065,0.0007130685,0.00020786,0.002233016],"category_scores_gemma":[0.00003136637,0.0006278204,0.0003124519,0.0006284032,0.0000720879,0.001361172,0.0004017646,0.0009514207,0.0003520402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002071669,"about_ca_system_score_gemma":0.0001038323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002673925,"about_ca_topic_score_gemma":0.00004142402,"domain_scores_codex":[0.9957218,0.0005299508,0.000776305,0.001464768,0.0008260582,0.0006811348],"domain_scores_gemma":[0.9975355,0.0005137484,0.0005804779,0.0005812242,0.0004397189,0.0003493852],"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":[0.0002328628,0.0004316892,0.00004576989,0.00007516635,0.00007133187,0.00003063518,0.0008370399,0.00006149685,0.002093306,0.0001690699,0.01758717,0.9783645],"study_design_scores_gemma":[0.01036153,0.007579835,0.002498799,0.001463201,0.0002602034,0.0007885262,0.00146672,0.8519876,0.01170941,0.04860035,0.05892719,0.004356638],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3124455,0.00003418718,0.6756808,0.002247351,0.006330946,0.001436525,0.0004285373,0.0006849629,0.0007111969],"genre_scores_gemma":[0.9823278,0.0002616273,0.006942505,0.006983439,0.001074069,0.0007379737,0.00123225,0.00007836505,0.0003619478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9740078,"threshold_uncertainty_score":0.9999071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0796470781317808,"score_gpt":0.3086133857295413,"score_spread":0.2289663075977605,"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."}}