{"id":"W4402981118","doi":"10.1109/icme57554.2024.10687820","title":"Spot the Difference! Temporal Coarse to Fine to Finer Difference Spotting for Action Recognition in Videos","year":2024,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Spotting; Computer science; Action (physics); Significant difference; Artificial intelligence; Temporal difference learning; Action recognition; Pattern recognition (psychology); Computer vision; Mathematics; Physics; Statistics; Reinforcement 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006225446,0.001206602,0.0009736018,0.0009752542,0.0003653228,0.0006929768,0.001783142,0.0008800967,0.004474191],"category_scores_gemma":[0.001732972,0.0003151138,0.0007216866,0.0007783707,0.0006919941,0.002110834,0.001338078,0.001686337,0.001539945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007455962,"about_ca_system_score_gemma":0.0007432526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007257984,"about_ca_topic_score_gemma":0.0107917,"domain_scores_codex":[0.9995826,0.00004168056,0.00001899145,0.000199381,0.000088878,0.000068548],"domain_scores_gemma":[0.9995509,0.0001136912,0.00005162754,0.0001319879,0.00008059821,0.00007132602],"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":[0.0006257189,0.0002385422,0.002566608,0.0001574559,0.0000720903,0.000194841,0.0001301315,0.03423453,0.04651447,0.005218744,0.009604347,0.9004425],"study_design_scores_gemma":[0.00003795012,0.0003119646,0.002659428,0.00002798854,0.00004460509,0.000304417,0.00008811348,0.9462868,0.03359398,0.009392235,0.007219485,0.00003298894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08776654,0.001385899,0.8936458,0.0005288037,0.0003695939,0.0002589902,0.001016205,0.009473227,0.005555002],"genre_scores_gemma":[0.6357963,0.000518157,0.3499871,0.0005990396,0.0001634697,0.0001474965,0.002427676,0.0003859723,0.00997471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007257984,"threshold_uncertainty_score":0.01496768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07937521943300895,"score_gpt":0.3137250345538831,"score_spread":0.2343498151208742,"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."}}