{"id":"W1963636698","doi":"10.1145/1877850.1877855","title":"A novel video thumbnail extraction method using spatiotemporal vector quantization","year":2010,"lang":"en","type":"article","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Codebook; Computer science; Vector quantization; Artificial intelligence; Thumbnail; Quantization (signal processing); Learning vector quantization; Pattern recognition (psychology); Gaussian; Computer vision; Feature vector; Image (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":[0.0005984448,0.0001067197,0.000132995,0.0001616555,0.0001688554,0.0002808661,0.0002833726,0.00009493964,0.00009664935],"category_scores_gemma":[0.0001110929,0.00009362365,0.00007644371,0.0005994427,0.0000131784,0.001155476,0.00006444789,0.0001432416,0.00002226267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002417787,"about_ca_system_score_gemma":0.00007113737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000778259,"about_ca_topic_score_gemma":0.0007851376,"domain_scores_codex":[0.998928,0.00005768446,0.0002670638,0.0003306084,0.0002656786,0.0001509317],"domain_scores_gemma":[0.9991442,0.00006617287,0.000158084,0.0004015744,0.0001685193,0.00006147464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000031624,0.00009232867,0.002846676,0.000005096598,0.00002007777,0.000001038945,0.0001942118,0.002132489,0.8119519,0.1503019,0.0001086134,0.03234251],"study_design_scores_gemma":[0.0001445227,0.00001339793,0.007104421,0.00000375539,0.00001420171,0.00001322719,0.00001021921,0.9696726,0.02098953,0.0008440322,0.001055084,0.0001350762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02394045,0.000004611319,0.9739053,0.0005077397,0.0005561216,0.00008564481,7.017044e-7,0.0001397171,0.0008597287],"genre_scores_gemma":[0.5287907,9.326164e-7,0.4708484,0.00009945741,0.00008593502,0.000001907863,0.000006485932,0.00000584002,0.0001603927],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.96754,"threshold_uncertainty_score":0.3817861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519305887254155,"score_gpt":0.3276503988354235,"score_spread":0.292457339962882,"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."}}