{"id":"W2782981605","doi":"10.1016/j.jvcir.2018.01.002","title":"Early event detection based on dynamic images of surveillance videos","year":2018,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; McGill University; Nvidia","keywords":"Computer science; Event (particle physics); Artificial intelligence; Set (abstract data type); Spotting; CLIPS; Computer vision; Detector; Pattern recognition (psychology)","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":[0.0005648165,0.00007653681,0.0001397028,0.0002136328,0.0001498941,0.000082754,0.0003482794,0.00003924788,0.000007121855],"category_scores_gemma":[0.0001097034,0.00007021964,0.000071662,0.0003584788,0.0001307772,0.0005318372,0.00007372053,0.0001372183,0.000004487772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003785718,"about_ca_system_score_gemma":0.00002933952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003107883,"about_ca_topic_score_gemma":0.000006321598,"domain_scores_codex":[0.9989013,0.0002304025,0.0004383903,0.0001232438,0.0002328437,0.00007378725],"domain_scores_gemma":[0.998067,0.0001771654,0.0006580916,0.0004419261,0.0006091037,0.00004675823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002130996,0.0005726546,0.002696021,0.00003485159,0.0000416309,0.000001428766,0.0006396482,0.0001043859,0.5610806,0.00125083,0.0003386926,0.4330261],"study_design_scores_gemma":[0.001047622,0.002566144,0.2262954,0.0001154582,0.00001958731,0.00004991464,0.000177309,0.3057859,0.460077,0.002915423,0.0007243404,0.0002259392],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1411386,0.00006154283,0.8576719,0.000607038,0.00004365589,0.000117243,0.000001217483,0.00002998501,0.000328788],"genre_scores_gemma":[0.9647757,0.0001941879,0.03490198,0.00005981131,0.00002639451,0.000007275432,0.00000186808,0.000005912019,0.00002691781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.823637,"threshold_uncertainty_score":0.2863474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01216606330296818,"score_gpt":0.3489642419550765,"score_spread":0.3367981786521083,"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."}}