{"id":"W2526371976","doi":"10.1109/tpami.2016.2613865","title":"Multi-Instance Classification by Max-Margin Training of Cardinality-Based Markov Networks","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Discriminative model; Multiclass classification; Margin (machine learning); Benchmark (surveying); Probabilistic logic; Machine learning; Graphical model; Ambiguity; Inference; Maximum-entropy Markov model; Cardinality (data modeling); Pattern recognition (psychology); Markov chain; Binary number; Markov model; Data mining; Variable-order Markov model; Mathematics; Support vector machine","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":[0.0004294525,0.0001999647,0.0003432655,0.0003023876,0.000129361,0.00006069013,0.0004613374,0.0000869236,0.00006245363],"category_scores_gemma":[0.000007973555,0.000146081,0.0002501157,0.0009560147,0.0001370431,0.0002293948,0.000003698001,0.0001543438,0.000005411875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005055707,"about_ca_system_score_gemma":0.00002881859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001687738,"about_ca_topic_score_gemma":0.00008560402,"domain_scores_codex":[0.9983569,0.0001427633,0.0004846414,0.000521786,0.0002751026,0.000218812],"domain_scores_gemma":[0.9987507,0.0002027871,0.0002277011,0.0005730756,0.0001423445,0.0001033523],"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":[0.00001922441,0.0001378252,0.0005745314,0.00001373027,0.0001572858,0.000001137104,0.00008664033,0.0004445737,0.0124164,0.00009574747,0.0000120314,0.9860409],"study_design_scores_gemma":[0.000160295,0.0001049635,0.001609253,0.0000608418,0.0001787572,0.000001908623,0.000033035,0.509409,0.4879401,0.00006570975,0.0001793678,0.0002568642],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005133986,0.000136383,0.9980597,0.0008533889,0.00007948439,0.0001326728,0.00007278262,0.0001170427,0.00003517428],"genre_scores_gemma":[0.9901681,0.0004566845,0.008906407,0.0001893239,0.000008104367,0.00003523715,0.000005447511,0.000009842292,0.0002208573],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9896547,"threshold_uncertainty_score":0.5957012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03734524230840205,"score_gpt":0.2818314518083433,"score_spread":0.2444862094999412,"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."}}