{"id":"W4411687687","doi":"10.1109/tii.2025.3577686","title":"TransCLIP: Transferring Vision–Language Models for Efficient Video Action Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"China Postdoctoral Science Foundation","keywords":"Computer science; Action recognition; Computer vision; Action (physics); Artificial intelligence; Speech recognition","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":[0.0006596973,0.00158371,0.0007315463,0.0005489165,0.000245597,0.0007637576,0.002372424,0.000968218,0.005743677],"category_scores_gemma":[0.002040687,0.0004563977,0.0009581681,0.0004188392,0.0004999035,0.001697903,0.001593748,0.002528868,0.003034358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000868,"about_ca_system_score_gemma":0.001012167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00727343,"about_ca_topic_score_gemma":0.009098779,"domain_scores_codex":[0.999625,0.00004456381,0.00001255446,0.0001913598,0.00006596005,0.00006061516],"domain_scores_gemma":[0.9996328,0.0001229248,0.0000279977,0.00009395884,0.00008659395,0.00003564266],"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":[0.0002668813,0.0003904415,0.0008596986,0.0001988591,0.0001127299,0.0001963718,0.0001196858,0.1146168,0.0420717,0.005047384,0.01685128,0.8192682],"study_design_scores_gemma":[0.00001726465,0.0001303932,0.0002712462,0.00001436893,0.00001940928,0.00006722714,0.00002063584,0.9819271,0.01150169,0.003356802,0.002660609,0.00001334471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01838271,0.0005357623,0.9604839,0.0001708574,0.0001790195,0.0002014898,0.0004105394,0.01650046,0.003135144],"genre_scores_gemma":[0.4856668,0.0006983861,0.4897585,0.00104937,0.0001800543,0.0006627021,0.003499431,0.001276044,0.01720883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00727343,"threshold_uncertainty_score":0.01921451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0812729455304916,"score_gpt":0.3095092651723503,"score_spread":0.2282363196418587,"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."}}