{"id":"W2801004733","doi":"10.1109/wacv.2018.00181","title":"Scaling Human-Object Interaction Recognition Through Zero-Shot Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":163,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Object (grammar); Object detection; Cognitive neuroscience of visual object recognition; Variety (cybernetics); Pattern recognition (psychology); Machine learning; Scaling; Action (physics); Histogram; Computer vision; Image (mathematics); 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000287964,0.0001274886,0.0001085284,0.00009282581,0.000582697,0.0002263832,0.0004142841,0.00006306942,0.0002699076],"category_scores_gemma":[0.0001546237,0.0001238534,0.00005467257,0.0003819583,0.00004399486,0.0007900406,0.0001752234,0.0003531706,0.001748038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005827864,"about_ca_system_score_gemma":0.00001819839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001057226,"about_ca_topic_score_gemma":0.00002876762,"domain_scores_codex":[0.9987851,0.0001215091,0.0002316644,0.0004410784,0.0001885081,0.0002321695],"domain_scores_gemma":[0.9991288,0.0001496516,0.0001293286,0.0003773304,0.0001648544,0.00005008341],"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":[0.0000280692,0.0003818993,0.009094944,0.00004457332,0.0000891814,0.000006128615,0.01197382,0.003149186,0.1178313,0.1003146,0.002924233,0.754162],"study_design_scores_gemma":[0.0009875519,0.0006357144,0.02402682,0.0001598354,0.00002944742,0.0000888283,0.0003765786,0.8044469,0.078698,0.05607014,0.03343181,0.001048301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2022516,0.000004648016,0.7369472,0.0004939369,0.0002061147,0.0001188074,2.458295e-7,0.0006881724,0.05928927],"genre_scores_gemma":[0.8975622,0.000002460417,0.1013808,0.000326576,0.0002284657,0.0000282214,0.00001400951,0.00001336778,0.0004439506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8012978,"threshold_uncertainty_score":0.9990292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0710747672886309,"score_gpt":0.3634047171561183,"score_spread":0.2923299498674874,"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."}}