{"id":"W1945428711","doi":"10.5220/0004684000680075","title":"Combining Dense Features with Interest Regions for Efficient Part-based Image Matching","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Histogram; Artificial intelligence; Pattern recognition (psychology); Matching (statistics); Representation (politics); Weighting; Region of interest; Benchmark (surveying); Image (mathematics); Clutter; Computation; Voting; Computer vision; Vocabulary; Noise (video); Mathematics; Algorithm","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":[0.0002721203,0.0001492826,0.0001592119,0.00008376372,0.0001914546,0.0002044653,0.0004828785,0.00003727876,0.000002979972],"category_scores_gemma":[0.0001008434,0.0001065151,0.00006327261,0.0001959876,0.0000641385,0.000237715,0.000108039,0.000124479,0.000006059679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000234319,"about_ca_system_score_gemma":0.00003012223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009681274,"about_ca_topic_score_gemma":0.00001654893,"domain_scores_codex":[0.9990405,0.0000412627,0.0001526724,0.0003494417,0.0001346895,0.0002813917],"domain_scores_gemma":[0.9988543,0.0003449218,0.00008527897,0.000508747,0.0001216393,0.00008511909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001167317,0.0001949813,0.00004654988,0.00007563231,0.00002122756,0.00002077958,0.000439651,0.0005705749,0.01064563,0.951789,0.007902094,0.0281771],"study_design_scores_gemma":[0.002329809,0.001787105,0.0002980599,0.0005192556,0.00003037801,0.00007363633,0.0001597717,0.09889933,0.7888033,0.07183336,0.03428238,0.0009836573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002731267,0.00002078443,0.9936931,0.00123301,0.00007547842,0.0002698207,0.000001370763,0.0006142807,0.001360898],"genre_scores_gemma":[0.4660036,0.00000117985,0.5326861,0.0009849709,0.00002920392,0.00003266374,0.000002755841,0.00001272392,0.0002468492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8799557,"threshold_uncertainty_score":0.4343561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02352534762414076,"score_gpt":0.2877512991288004,"score_spread":0.2642259515046596,"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."}}