{"id":"W4392199017","doi":"10.1145/3649466","title":"An Optimal Edge-weighted Graph Semantic Correlation Framework for Multi-view Feature Representation Learning","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Graph; Computer science; Feature learning; Representation (politics); Correlation; Feature (linguistics); Enhanced Data Rates for GSM Evolution; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Mathematics; Geometry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001966775,0.001694229,0.002075048,0.002257062,0.0006284207,0.001413835,0.002739466,0.001676495,0.002572588],"category_scores_gemma":[0.004585048,0.0006631103,0.001864124,0.004095191,0.001243064,0.003305255,0.002180733,0.002549601,0.0008927381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001052077,"about_ca_system_score_gemma":0.001857103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005729632,"about_ca_topic_score_gemma":0.005366859,"domain_scores_codex":[0.9980343,0.0006577371,0.00008232026,0.0005757048,0.000501705,0.00014817],"domain_scores_gemma":[0.99844,0.0005508576,0.0001707542,0.0002648458,0.000478813,0.00009471455],"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":[0.0002020257,0.0002261157,0.001383719,0.0003557011,0.000258508,0.000179856,0.0001588184,0.41197,0.009075726,0.06802534,0.01151529,0.4966489],"study_design_scores_gemma":[0.000008121736,0.00004477203,0.0001533826,0.000009109255,0.00001932352,0.00003773849,0.00001433422,0.9837942,0.0007322495,0.01440394,0.0007683047,0.00001456387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002746636,0.0001870514,0.9963581,0.00008274289,0.00001689516,0.00002673209,0.0000619165,0.0002248102,0.0002952007],"genre_scores_gemma":[0.2464607,0.0009739192,0.7472994,0.0004056412,0.000185362,0.0004519088,0.001506622,0.0003161699,0.002400155],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005729632,"threshold_uncertainty_score":0.01139259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04322333769696318,"score_gpt":0.3769415209404004,"score_spread":0.3337181832434372,"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."}}