{"id":"W4319300119","doi":"10.1109/wacv56688.2023.00301","title":"MixVPR: Feature Mixing for Visual Place Recognition","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Nature","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Margin (machine learning); Process (computing); Cascade; Pattern recognition (psychology); Latency (audio); Set (abstract data type); Scale (ratio); Feature extraction; Precision and recall; Computer vision; Machine learning; Engineering","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":[0.0006450074,0.002038584,0.001773092,0.003306094,0.0005710315,0.001333741,0.003647072,0.001220618,0.008699508],"category_scores_gemma":[0.001364127,0.0006973908,0.00131581,0.002750431,0.000544949,0.002877244,0.002917718,0.0012236,0.007738328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007237904,"about_ca_system_score_gemma":0.0007500984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005663404,"about_ca_topic_score_gemma":0.009606825,"domain_scores_codex":[0.9989975,0.00006861485,0.0000462707,0.0003580605,0.0003929301,0.0001365615],"domain_scores_gemma":[0.9995442,0.00006141637,0.00004520189,0.0002011257,0.0001122016,0.00003577496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002784161,0.0001607579,0.0008587107,0.0001783147,0.0001023301,0.0001410385,0.00006765486,0.00874571,0.0338888,0.001741696,0.02008795,0.9337486],"study_design_scores_gemma":[0.0002256516,0.0008107289,0.004671182,0.00007393586,0.000189194,0.001888493,0.0002955114,0.7656623,0.1577389,0.01471638,0.05358896,0.0001388106],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03459365,0.001905,0.887817,0.0001755634,0.0002853654,0.000328174,0.002663745,0.06760465,0.004626858],"genre_scores_gemma":[0.2918966,0.0007859535,0.6764772,0.0003862907,0.0001905186,0.0003157644,0.01292142,0.001938291,0.01508807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008699508,"threshold_uncertainty_score":0.02910274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03833107397971237,"score_gpt":0.3512669887496743,"score_spread":0.3129359147699619,"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."}}