{"id":"W1980508392","doi":"10.1109/tip.2012.2214049","title":"Video Object Tracking in the Compressed Domain Using Spatio-Temporal Markov Random Fields","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer vision; Artificial intelligence; Video tracking; Motion compensation; Computer science; Motion estimation; Markov random field; Block-matching algorithm; Block (permutation group theory); Markov chain; Pixel; Pattern recognition (psychology); Object (grammar); Mathematics; Image segmentation; Image (mathematics); Machine learning","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":[0.002270517,0.0002423059,0.0002897743,0.0002418062,0.0005405831,0.0005324852,0.0006454346,0.0001079927,0.00001852949],"category_scores_gemma":[0.00002464005,0.0001920506,0.0001354679,0.0008520366,0.00008169827,0.002055384,0.000004487501,0.000547093,0.000008201688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006521888,"about_ca_system_score_gemma":0.00009990213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001185375,"about_ca_topic_score_gemma":0.0001068531,"domain_scores_codex":[0.9976283,0.0006337052,0.0004179885,0.0003585664,0.0004094991,0.0005519758],"domain_scores_gemma":[0.9987109,0.0005232143,0.0001475418,0.0004600489,0.00008150453,0.00007679114],"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":[0.0004123611,0.001220626,0.007358451,0.0003821137,0.00007339899,0.00009681267,0.03197553,0.01789975,0.01298585,0.0001057329,0.00009274974,0.9273966],"study_design_scores_gemma":[0.01324267,0.0003219378,0.02566617,0.001613018,0.000178157,0.0008080485,0.002493865,0.7839524,0.1610807,0.005874521,0.001779516,0.002988933],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07057287,0.0002681607,0.9274549,0.0004068553,0.0005342409,0.0002581057,0.000002414288,0.0001362532,0.0003661863],"genre_scores_gemma":[0.8146611,0.000007963583,0.1847858,0.000382859,0.0001012698,0.00003132744,9.938093e-7,0.00001783364,0.00001080226],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9244077,"threshold_uncertainty_score":0.7831594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03635832405567782,"score_gpt":0.3198126644037912,"score_spread":0.2834543403481133,"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."}}