{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003293311,0.0001562655,0.0001375104,0.000306917,0.0001422977,0.0004160476,0.0003140998,0.00005765212,0.0001330376],"category_scores_gemma":[0.0001163294,0.000108778,0.00007199521,0.0006540322,0.00001196144,0.0003350536,0.0001019486,0.0001654317,0.0004077348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007260033,"about_ca_system_score_gemma":0.00004694561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001694954,"about_ca_topic_score_gemma":0.001365427,"domain_scores_codex":[0.9987209,0.00005333669,0.0002881441,0.000463924,0.0001935259,0.0002801476],"domain_scores_gemma":[0.9992375,0.0003043509,0.00003612941,0.0002402443,0.00008478155,0.00009702356],"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":[0.00002816089,0.00005512965,0.0001982511,0.00004398157,0.000008071066,0.000006942963,0.000818944,0.00001619456,0.01261393,0.001486302,0.003705626,0.9810185],"study_design_scores_gemma":[0.002229102,0.001909825,0.1240107,0.002336643,0.00008366303,0.000123851,0.001053303,0.4698743,0.2187591,0.11133,0.0657663,0.002523239],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5587048,0.000008243879,0.4341618,0.0053256,0.0004956395,0.0005753452,0.00001155548,0.0002142006,0.0005028209],"genre_scores_gemma":[0.9801192,0.000004164558,0.01348424,0.001569162,0.0002607773,0.0003168927,0.0000266496,0.00001272335,0.004206242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9784952,"threshold_uncertainty_score":0.5240742,"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."}}