{"id":"W3196766446","doi":"10.48550/arxiv.2109.02613","title":"Class Semantics-based Attention for Action Detection","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Feature (linguistics); Action (physics); Encoder; Semantics (computer science); Class (philosophy); Artificial intelligence; Task (project management); Mechanism (biology); Pattern recognition (psychology); Attention network","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":[0.0006490564,0.001392192,0.0008311717,0.001629906,0.00041399,0.0006975068,0.002038368,0.001108114,0.005098609],"category_scores_gemma":[0.002144428,0.0003367503,0.0008987226,0.001195773,0.0006075157,0.002562613,0.001343371,0.00142108,0.001244008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001640716,"about_ca_system_score_gemma":0.001056374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0179113,"about_ca_topic_score_gemma":0.02469092,"domain_scores_codex":[0.9994387,0.00007959514,0.00002017042,0.0002802433,0.00009859727,0.00008267758],"domain_scores_gemma":[0.9994379,0.0002456892,0.00006126786,0.0001085793,0.000100252,0.00004641637],"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":[0.000416636,0.0002908302,0.004539019,0.0002733729,0.0001533961,0.000157646,0.0001305016,0.05026053,0.02742153,0.009361362,0.0226051,0.8843901],"study_design_scores_gemma":[0.00003703152,0.0001519309,0.004187137,0.00004340789,0.0001036712,0.0001918032,0.00005733307,0.9425334,0.01476087,0.03083465,0.007068538,0.00003024092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1053329,0.005347206,0.8590909,0.001211021,0.0004171543,0.0002385897,0.002175661,0.01238628,0.01380036],"genre_scores_gemma":[0.8856843,0.001129368,0.1005976,0.0007445743,0.0002299552,0.000142319,0.003047013,0.0003004073,0.008124511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0179113,"threshold_uncertainty_score":0.03561407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1187528620764375,"score_gpt":0.2121582252449545,"score_spread":0.09340536316851697,"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."}}