{"id":"W2997593239","doi":"10.1609/aaai.v34i04.5777","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","year":2020,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Samsung","keywords":"Computer science; Artificial intelligence; Scalability; Object (grammar); Computer vision; Video tracking; Architecture; Tracking (education); Invariant (physics); Cognitive neuroscience of visual object recognition; Process (computing); Computation; Track (disk drive); Object detection; Task (project management); Pattern recognition (psychology)","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":[0.0006482718,0.0001469837,0.0002336544,0.00003607577,0.0001810252,0.0002850345,0.0007034002,0.00005520276,0.00003219145],"category_scores_gemma":[0.0004975423,0.0001369873,0.0001043578,0.0003837698,0.00001836486,0.0006774102,0.0001365536,0.0001152154,0.00003933578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001594146,"about_ca_system_score_gemma":0.00007856105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006791001,"about_ca_topic_score_gemma":0.0000211021,"domain_scores_codex":[0.9985469,0.0001016771,0.0002688708,0.000508734,0.000198345,0.0003754932],"domain_scores_gemma":[0.9989565,0.0004166721,0.00007192281,0.0003104287,0.0001088193,0.0001356464],"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":[0.00006216735,0.00007816125,0.01279021,0.0002055044,0.00006163396,0.00003163721,0.003634688,0.001214285,0.02625515,0.04562938,0.001685127,0.9083521],"study_design_scores_gemma":[0.002292734,0.0003801333,0.01004683,0.00007398437,0.00001305166,0.0000133361,0.0001745757,0.8382624,0.1257015,0.00949548,0.01271855,0.0008274088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005061823,0.00006847778,0.9874645,0.003825407,0.0002851094,0.0002452838,0.000002241514,0.0004476427,0.002599496],"genre_scores_gemma":[0.6459481,0.000003761155,0.3512069,0.002502697,0.0002577552,0.00002535687,0.000001930781,0.00001250001,0.00004098688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9075246,"threshold_uncertainty_score":0.5586181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08860429258946417,"score_gpt":0.2951356565833494,"score_spread":0.2065313639938853,"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."}}