{"id":"W2990786707","doi":"10.1109/avss.2019.8909874","title":"Multi-Component Spatiotemporal Attention and its Application to Object Detection in Surveillance Videos","year":2019,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Robustness (evolution); Object detection; Artificial intelligence; Computer vision; Focus (optics); Interest point detection; Coherence (philosophical gambling strategy); Change detection; Object (grammar); Video tracking; Component (thermodynamics); Detector; Motion detection; Pattern recognition (psychology); Feature (linguistics); Motion (physics); Feature detection (computer vision); Image processing; Image (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":[],"consensus_categories":[],"category_scores_codex":[0.0003750923,0.0001050425,0.0001191552,0.0002239763,0.00005589907,0.00006978621,0.0001594291,0.00005729933,0.000008740717],"category_scores_gemma":[0.00001701278,0.0001029727,0.00003152082,0.000505164,0.000004904591,0.0004350565,0.00008413044,0.00008036155,0.0003534934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007302864,"about_ca_system_score_gemma":0.000009693963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002539505,"about_ca_topic_score_gemma":0.0009477866,"domain_scores_codex":[0.998872,0.00008319682,0.000241265,0.000448429,0.0001891086,0.0001660261],"domain_scores_gemma":[0.9995516,0.00001911919,0.00006869206,0.0002255833,0.00006708219,0.00006790067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002524104,0.0001455439,0.05280997,0.00003618917,0.000005239547,9.140098e-7,0.0002282858,0.0004275709,0.8558291,0.001430707,0.000007610616,0.0890536],"study_design_scores_gemma":[0.0004320632,0.0001011048,0.5579721,0.000008803585,5.376616e-7,0.000005112624,0.00002055816,0.4235814,0.01750739,0.00004940573,0.0001890406,0.000132556],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5826138,0.00001019891,0.4163624,0.0002165519,0.0002032797,0.0004098205,3.417781e-7,0.0001001234,0.00008345053],"genre_scores_gemma":[0.997241,0.000006015339,0.002210095,0.0001369101,0.00001728902,0.00005342999,0.000002884268,0.000006164181,0.0003261787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8383217,"threshold_uncertainty_score":0.454356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01386246011076164,"score_gpt":0.2677787404716446,"score_spread":0.2539162803608829,"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."}}