{"id":"W2130330575","doi":"10.1109/tpami.2011.91","title":"On Sensor Bias in Experimental Methods for Comparing Interest-Point, Saliency, and Recognition Algorithms","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Radiance; Shutter; Feature (linguistics); Offset (computer science); Image sensor; Machine vision; Pattern recognition (psychology); Algorithm; Optics","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":[0.0004955371,0.0002020194,0.000299765,0.0007265998,0.0001401576,0.00009364744,0.0001847404,0.00006278923,0.00007423345],"category_scores_gemma":[0.00000988046,0.0001816196,0.0001686686,0.0006129089,0.00005639343,0.00026429,0.000007112401,0.0001942873,0.00001189112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000367312,"about_ca_system_score_gemma":0.000005796257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000882717,"about_ca_topic_score_gemma":0.0007434681,"domain_scores_codex":[0.9985242,0.0001951596,0.0004055994,0.0005614615,0.000110117,0.0002034541],"domain_scores_gemma":[0.9993311,0.0001790089,0.0001030069,0.0002365818,0.00004830303,0.0001020109],"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":[0.00005404664,0.0004154974,0.0003567906,0.00001500797,0.0001250812,0.000003179458,0.001598155,0.000320956,0.001522972,0.0001504891,0.000001279129,0.9954365],"study_design_scores_gemma":[0.0002626748,0.0006609155,0.001168169,0.00004661807,0.0001080905,0.00001635222,0.0003809418,0.5113202,0.4840581,0.001694907,0.0000070722,0.0002760471],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08838102,0.00004275691,0.9109389,0.00004947418,0.0002447692,0.0001941555,0.000008678358,0.00005918827,0.00008101142],"genre_scores_gemma":[0.9727913,0.00007642578,0.02680176,0.0002174744,0.000008269429,0.00005100638,0.000003677276,0.000009653601,0.00004046268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9951605,"threshold_uncertainty_score":0.7406232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1704828686100905,"score_gpt":0.3813700416059017,"score_spread":0.2108871729958112,"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."}}