{"id":"W2807771925","doi":"10.24963/ijcai.2018/119","title":"H-Net: Neural Network for Cross-domain Image Patch Matching","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Rendering (computer graphics); Net (polyhedron); Image (mathematics); Domain (mathematical analysis); Autoencoder; Benchmark (surveying); Matching (statistics); Computer vision; Pattern recognition (psychology); Artificial neural network; Feature (linguistics); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008049909,0.001319591,0.001090239,0.001094278,0.0004780819,0.0008196075,0.002480761,0.001601595,0.00679053],"category_scores_gemma":[0.001730374,0.0005493082,0.0008858323,0.001034578,0.0005410889,0.001785921,0.001322604,0.001357507,0.002113788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057888,"about_ca_system_score_gemma":0.0008637062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009895494,"about_ca_topic_score_gemma":0.00985287,"domain_scores_codex":[0.9996332,0.00003676659,0.00002244553,0.0001628434,0.00008236719,0.00006246584],"domain_scores_gemma":[0.9995959,0.0001085753,0.00003812245,0.00008828859,0.0001342446,0.00003477151],"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":[0.0006619911,0.0003476049,0.002061679,0.0002284207,0.0002596326,0.0001908455,0.00005803228,0.2018867,0.0157652,0.003348669,0.02082107,0.7543703],"study_design_scores_gemma":[0.00002551551,0.0000649713,0.0003693802,0.000007771408,0.00002042218,0.00004658952,0.00001389356,0.9909626,0.005195908,0.001898494,0.001384425,0.00001001775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04527433,0.001427424,0.9320145,0.000333928,0.000303665,0.0002851977,0.001052669,0.014428,0.004880198],"genre_scores_gemma":[0.4470159,0.0007225312,0.5298136,0.0008071887,0.0001757528,0.0003917626,0.005464444,0.0007588404,0.01485013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009895494,"threshold_uncertainty_score":0.02271652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01762113836595273,"score_gpt":0.3301202068268898,"score_spread":0.312499068460937,"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."}}