{"id":"W2110271102","doi":"10.1109/cvprw.2008.4563042","title":"Learning the abstract motion semantics of verbs from captioned videos","year":2008,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Semantics (computer science); Computer science; Motion (physics); Verb; Action (physics); Set (abstract data type); Artificial intelligence; Natural language processing; Space (punctuation); Test set; Machine learning; Programming language","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":[0.0007559385,0.001246571,0.0009046376,0.001457732,0.0003874475,0.001241549,0.001637408,0.001580552,0.00204985],"category_scores_gemma":[0.004492659,0.0004626375,0.0009392021,0.001238515,0.0007987779,0.002764572,0.000798924,0.001558929,0.0005764989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008421547,"about_ca_system_score_gemma":0.0009983663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003834219,"about_ca_topic_score_gemma":0.004094512,"domain_scores_codex":[0.999469,0.0001070024,0.00003900643,0.0002434612,0.00008885518,0.0000526676],"domain_scores_gemma":[0.9992011,0.0004250406,0.0001103901,0.0001045738,0.0001138803,0.00004494282],"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":[0.0007613387,0.0004257303,0.00438485,0.0004626648,0.000133393,0.0003491072,0.0005161479,0.163351,0.03533127,0.02953308,0.007555515,0.7571959],"study_design_scores_gemma":[0.00005628779,0.0001256363,0.0007784515,0.00003452449,0.0000239008,0.0001105311,0.0001551185,0.9562156,0.005158915,0.03556757,0.001753901,0.00001954859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04331213,0.0001853453,0.9533173,0.0002372072,0.00004303556,0.0001368587,0.0004550085,0.00156029,0.0007527746],"genre_scores_gemma":[0.5165694,0.0003649716,0.4769996,0.0002056207,0.00008767126,0.0003817283,0.003669511,0.0001721225,0.00154944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003834219,"threshold_uncertainty_score":0.007623792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02734010832257521,"score_gpt":0.2259662953526192,"score_spread":0.198626187030044,"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."}}