{"id":"W4409263175","doi":"10.1109/wacv61041.2025.00714","title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","year":2025,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Computer science; Embedding; Joint (building); Point cloud; Architecture; Artificial intelligence; Cloud computing; Machine learning; Point (geometry); Mathematics; Engineering; Operating system; Geography","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":[0.001084634,0.001338279,0.001128413,0.0007887306,0.0004610792,0.0009778958,0.004043685,0.001543193,0.003712098],"category_scores_gemma":[0.002907043,0.0007774119,0.001183738,0.0009584937,0.0007294957,0.002228054,0.00251319,0.002696466,0.002525658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007640073,"about_ca_system_score_gemma":0.001010371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008282855,"about_ca_topic_score_gemma":0.01190777,"domain_scores_codex":[0.9993609,0.0001143707,0.00002578764,0.0002504646,0.0001821559,0.00006648079],"domain_scores_gemma":[0.9991881,0.0002229361,0.00005547483,0.0002570387,0.0002170556,0.00005940414],"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":[0.000290387,0.0003294122,0.002733095,0.0001998747,0.0002930254,0.000154863,0.0001581559,0.3422112,0.01309519,0.005421896,0.01827625,0.6168366],"study_design_scores_gemma":[0.000007498209,0.00003064074,0.0001836522,0.000006672678,0.000008112655,0.00002455831,0.000006813428,0.9947295,0.001873228,0.00211982,0.001001907,0.000007673104],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01514353,0.0005152687,0.968735,0.0001532084,0.0001010715,0.0001123395,0.0003696544,0.01362892,0.001240938],"genre_scores_gemma":[0.4227421,0.0006611056,0.559548,0.0006458042,0.000159915,0.0005591438,0.005450421,0.001267346,0.008966126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008282855,"threshold_uncertainty_score":0.01646924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007715015214383938,"score_gpt":0.2250212482545431,"score_spread":0.2173062330401591,"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."}}