{"id":"W3135446078","doi":"10.1109/tcsvt.2021.3063001","title":"Feature Aggregation Networks Based on Dual Attention Capsules for Visual Object Tracking","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"China Scholarship Council; National Natural Science Foundation of China; Compute Canada","keywords":"Computer science; Artificial intelligence; Discriminative model; Convolutional neural network; Pattern recognition (psychology); Feature (linguistics); Histogram of oriented gradients; Feature vector; BitTorrent tracker; Feature learning; Feature extraction; Video tracking; Computer vision; Eye tracking; Histogram; Object (grammar); Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007001152,0.0002436953,0.0003968123,0.0004221698,0.0005314735,0.0002430181,0.0002114414,0.0004048227,9.964343e-7],"category_scores_gemma":[0.00006594733,0.0002377658,0.0001918576,0.0006549057,0.00006001075,0.0002328738,0.000002382313,0.0003097335,0.000001671372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007512898,"about_ca_system_score_gemma":0.00009447517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000922787,"about_ca_topic_score_gemma":0.00005966929,"domain_scores_codex":[0.9982072,0.0001487371,0.0003209457,0.000712542,0.0002019414,0.0004086489],"domain_scores_gemma":[0.9983791,0.0005900305,0.0001723913,0.0004682226,0.0003255274,0.00006471066],"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":[0.00006815705,0.000376486,0.0002990316,0.0004525346,0.0001839629,0.00004145273,0.00009717213,0.06839107,0.01160588,0.01578696,0.000369846,0.9023275],"study_design_scores_gemma":[0.002619898,0.001184061,0.0006189,0.0006127427,0.00008386187,0.0002460266,0.0002158613,0.9523122,0.036264,0.001310534,0.003932829,0.0005991145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0115993,0.0006475639,0.9832966,0.001361177,0.001834781,0.0007760499,0.00004260505,0.0004123258,0.0000296231],"genre_scores_gemma":[0.9948727,0.00005452658,0.004135356,0.0001750671,0.0001238458,0.0004566167,0.00001380896,0.00003020622,0.0001378122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9832734,"threshold_uncertainty_score":0.9695808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02583028711931734,"score_gpt":0.2878912115274279,"score_spread":0.2620609244081105,"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."}}