{"id":"W4413147250","doi":"10.1109/cvpr52734.2025.00189","title":"Exploring Temporally-Aware Features for Point Tracking","year":2025,"lang":"en","type":"article","venue":"","topic":"Human Motion and Animation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Creative Content Agency; National Research Foundation","keywords":"Computer science; Point (geometry); Tracking (education); Artificial intelligence; Computer vision; Mathematics","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":[0.00004732881,0.00005244297,0.00005452318,0.00006654331,0.00004286238,0.00003798498,0.00003726511,0.00001935972,0.00006083927],"category_scores_gemma":[0.000009875507,0.00004982585,0.00003441961,0.00005659824,0.000002843177,0.0001805161,0.000004964058,0.00004144883,0.00001083872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002328907,"about_ca_system_score_gemma":0.000003458381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001957626,"about_ca_topic_score_gemma":0.00001396515,"domain_scores_codex":[0.9997397,0.000002535741,0.00008391547,0.00006057528,0.00003157987,0.00008170893],"domain_scores_gemma":[0.9998888,0.00001569818,0.000005081766,0.00005591601,0.00001927649,0.00001526054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003210542,0.00008900738,0.00114911,0.002038585,0.0002025389,0.000005140482,0.003745826,0.03580103,0.05257927,0.2789981,0.1906278,0.4347315],"study_design_scores_gemma":[0.003795569,0.0001326721,0.1136123,0.001101131,0.00008220181,0.000006709283,0.006483505,0.2453295,0.3338884,0.01631308,0.2776899,0.001564944],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1412687,0.0001465176,0.7689329,0.000863307,0.0009669832,0.0004213106,0.000005451761,0.001777715,0.08561713],"genre_scores_gemma":[0.996443,0.00001205773,0.00143168,0.00008789583,0.00005183457,0.00004056468,0.000007890392,0.00000919285,0.001915851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8551743,"threshold_uncertainty_score":0.2031839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0843292876587925,"score_gpt":0.2668678391953821,"score_spread":0.1825385515365896,"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."}}