{"id":"W2991085797","doi":"10.1609/aaai.v34i04.5777","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Samsung","keywords":"Computer science; Scalability; Artificial intelligence; Object (grammar); Architecture; Computer vision; Invariant (physics); Video tracking; Tracking (education); Process (computing); Computation; Track (disk drive); Cognitive neuroscience of visual object recognition; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006048667,0.0005379059,0.000623602,0.0005941118,0.0003470479,0.0005745071,0.001767546,0.0006616561,0.001608771],"category_scores_gemma":[0.001432286,0.0003548228,0.0005982601,0.0008819742,0.0005268001,0.001162519,0.001165513,0.0008314363,0.0006201634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007698294,"about_ca_system_score_gemma":0.0009363359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008430123,"about_ca_topic_score_gemma":0.0113919,"domain_scores_codex":[0.9997019,0.00003380878,0.00001426235,0.0001162471,0.00007756544,0.00005606171],"domain_scores_gemma":[0.999501,0.0001458471,0.00006330992,0.0001758346,0.00007845694,0.00003564265],"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":[0.000214757,0.0001927109,0.001625944,0.0000878914,0.0001123687,0.0001223885,0.0001248383,0.3986128,0.09404346,0.01800073,0.004804739,0.4820574],"study_design_scores_gemma":[0.000005132799,0.00002344171,0.0003116634,0.000002078012,0.000008668537,0.00002769219,0.000005324892,0.9890351,0.005683966,0.004241856,0.0006496151,0.000005475099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03088694,0.0002050384,0.9646135,0.00009248241,0.00003457984,0.00002545812,0.00007109778,0.002368739,0.001702231],"genre_scores_gemma":[0.6553282,0.0003161916,0.3385717,0.0002380635,0.00006329188,0.00008277332,0.0005688772,0.0002123879,0.004618433],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008430123,"threshold_uncertainty_score":0.01676214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2092067776053434,"score_gpt":0.3441807439909045,"score_spread":0.1349739663855611,"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."}}