{"id":"W2005219154","doi":"10.1109/robot.2010.5509703","title":"Viewpoint detection models for sequential embodied object category recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Viewpoints; Cognitive neuroscience of visual object recognition; Artificial intelligence; Object (grammar); Object detection; Component (thermodynamics); Embodied cognition; Computer vision; 3D single-object recognition; Pattern recognition (psychology); Machine learning; Visualization","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":[],"consensus_categories":[],"category_scores_codex":[0.0002869284,0.0001160441,0.0001174621,0.00009637305,0.0001347698,0.0001000521,0.0002881498,0.00009428791,0.00001997695],"category_scores_gemma":[0.00006691848,0.0001025797,0.00009308704,0.0001681062,0.00002738438,0.001261091,0.00008162779,0.000179856,0.00002602637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002501398,"about_ca_system_score_gemma":0.00003665992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004345172,"about_ca_topic_score_gemma":0.0000889786,"domain_scores_codex":[0.9991192,0.00002132178,0.0001913833,0.0003304615,0.0001231177,0.0002145496],"domain_scores_gemma":[0.9992951,0.00005505072,0.00007136517,0.0003237432,0.0001939982,0.00006079235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001982982,0.00003015285,4.165772e-7,0.00001534483,0.000006355552,0.000001508558,0.00007129166,0.000009312389,0.1927534,0.02615806,0.000255083,0.7806792],"study_design_scores_gemma":[0.0001362942,0.00009334928,0.000003293708,0.000003113756,0.000003854559,0.00001255562,0.000003916664,0.04972553,0.5672154,0.3812734,0.001415215,0.0001140106],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001049373,0.00001815349,0.9907877,0.0002472243,0.0004629075,0.0004206026,0.00000282197,0.0006911603,0.006320056],"genre_scores_gemma":[0.6158839,0.00002928605,0.3830087,0.0005718873,0.0001413082,0.0001183824,0.000007328038,0.00001239955,0.0002267748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7805653,"threshold_uncertainty_score":0.418308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04398635365548369,"score_gpt":0.2992980365365113,"score_spread":0.2553116828810276,"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."}}