{"id":"W2112686133","doi":"10.1109/tcsvt.2009.2017304","title":"Places Clustering of Full-Length Film Key-Frames Using Latent Aspect Modeling Over SIFT Matches","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Key (lock); Cluster analysis; Computer science; Key frame; Artificial intelligence; Pattern recognition (psychology); Probabilistic latent semantic analysis; Scale-invariant feature transform; Constant false alarm rate; Matching (statistics); Probabilistic logic; Set (abstract data type); Feature extraction; Computer vision; Data mining; Mathematics; Frame (networking); Statistics","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":[0.0002766789,0.0005944346,0.0008354521,0.002686407,0.0004201851,0.0009131986,0.001020623,0.0004892596,0.001148759],"category_scores_gemma":[0.000861283,0.0001938977,0.0009356492,0.002423804,0.0003457621,0.000780247,0.0006479094,0.0005978636,0.001007408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006673615,"about_ca_system_score_gemma":0.0006138605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007139314,"about_ca_topic_score_gemma":0.01132136,"domain_scores_codex":[0.9995117,0.00004259814,0.00002694884,0.0001782184,0.0001562713,0.00008422448],"domain_scores_gemma":[0.9995809,0.00005785505,0.00009288328,0.0001000914,0.0001368721,0.00003136912],"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":[0.0007071233,0.0002940578,0.01152955,0.0002705574,0.000192821,0.0003583377,0.0003104188,0.04053565,0.0910103,0.005524641,0.006263833,0.8430027],"study_design_scores_gemma":[0.00002442514,0.0001299519,0.01287385,0.00001953171,0.0000702889,0.0003328752,0.0002499434,0.9470448,0.03120357,0.003809492,0.004197801,0.00004329845],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1141176,0.0003444012,0.8805323,0.00007339742,0.00004873076,0.0002052968,0.0007300101,0.002322134,0.001626123],"genre_scores_gemma":[0.7122385,0.0002548141,0.2813636,0.00003401528,0.00005814783,0.0001341123,0.002545652,0.0001937003,0.003177445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007139314,"threshold_uncertainty_score":0.01419556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03566429694593028,"score_gpt":0.2847007954399047,"score_spread":0.2490364984939745,"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."}}