{"id":"W3203857058","doi":"10.1109/iccv48922.2021.00971","title":"High-Performance Discriminative Tracking with Transformers","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Research and Development; National Natural Science Foundation of China","keywords":"Discriminative model; Computer science; Artificial intelligence; Robustness (evolution); Video tracking; Minimum bounding box; Pattern recognition (psychology); Computer vision; BitTorrent tracker; Encoder; Transformer; Object detection; Eye tracking; Object (grammar); Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005166256,0.0004043473,0.0004249389,0.0002560942,0.0002369304,0.000778367,0.001225987,0.0001146614,0.0003515074],"category_scores_gemma":[0.00002601624,0.0003368496,0.0001410109,0.00056508,0.00009303298,0.001309406,0.0001766533,0.0004884604,0.0001583572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001531843,"about_ca_system_score_gemma":0.000290454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002715215,"about_ca_topic_score_gemma":0.00004573845,"domain_scores_codex":[0.9966545,0.0002583713,0.0005014484,0.00104798,0.001072172,0.0004655258],"domain_scores_gemma":[0.9977819,0.0002643322,0.0002076703,0.0005890611,0.0009898118,0.0001672752],"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":[0.0001519155,0.0004370266,0.0008037746,0.00004302646,0.000217858,0.000454957,0.001119596,0.004761705,0.003878125,0.08194441,0.0009940537,0.9051936],"study_design_scores_gemma":[0.003561457,0.002102875,0.0433658,0.001618147,0.00003899848,0.0003874241,0.0002253543,0.834169,0.1025617,0.004432013,0.005813807,0.00172345],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1226324,0.00002345202,0.8618357,0.005380659,0.003179347,0.0001639571,0.00001785117,0.0001432026,0.006623443],"genre_scores_gemma":[0.9019622,0.0001644193,0.09590646,0.0007924469,0.0003913446,0.00002263531,0.00004359828,0.00002534341,0.0006915238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9034701,"threshold_uncertainty_score":0.9999083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04434457477481431,"score_gpt":0.3145527255423552,"score_spread":0.2702081507675409,"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."}}