{"id":"W2992282318","doi":"10.1109/crv50864.2020.00012","title":"Tree bark re-identification using a deep-learning feature descriptor","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Nvidia","keywords":"Artificial intelligence; Scale-invariant feature transform; Computer science; Tree (set theory); Benchmark (surveying); Context (archaeology); Identification (biology); Bark (sound); Pattern recognition (psychology); Deep learning; Feature (linguistics); Computer vision; Pixel; Feature extraction; Geography; Mathematics; Cartography","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003004043,0.000342438,0.0003660568,0.0001690226,0.000190839,0.0007352378,0.001569662,0.0003393256,0.0000298422],"category_scores_gemma":[0.00036785,0.0003314557,0.0001971086,0.0004883935,0.00004031824,0.0007020899,0.002033439,0.001265629,0.00003855496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001426795,"about_ca_system_score_gemma":0.0001183164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003700738,"about_ca_topic_score_gemma":0.000007308076,"domain_scores_codex":[0.9976836,0.0001476646,0.0003738692,0.001071912,0.0004093853,0.0003135551],"domain_scores_gemma":[0.9982339,0.00006082794,0.0003587349,0.0009680871,0.0002293202,0.0001491545],"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":[0.00004957123,0.0001120896,0.0003955056,0.0005740768,0.0001595895,0.000184406,0.002852817,0.001171532,0.1793328,0.01387524,0.01563443,0.7856579],"study_design_scores_gemma":[0.0002565751,0.0001235432,0.001014406,0.0003808399,0.00007597428,0.00003114294,0.0002043462,0.7070756,0.2104639,0.05203729,0.02701319,0.001323187],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002693516,0.0007795781,0.9924654,0.001028283,0.0004981264,0.0004108027,0.000001936551,0.001555344,0.002991167],"genre_scores_gemma":[0.150914,0.0002244149,0.8462698,0.0004948881,0.0002667928,0.00003053727,0.00003005891,0.00004121578,0.001728263],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7843348,"threshold_uncertainty_score":0.9999138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05339177991491928,"score_gpt":0.3161994344480458,"score_spread":0.2628076545331265,"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."}}