{"id":"W2810966399","doi":"10.1016/j.image.2018.06.018","title":"RevHashNet: Perceptually de-hashing real-valued image hashes for similarity retrieval","year":2018,"lang":"en","type":"article","venue":"Signal Processing Image Communication","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Qatar National Research Fund; National Natural Science Foundation of China; Qatar Foundation","keywords":"Hash function; Computer science; Image retrieval; Locality-sensitive hashing; Artificial intelligence; Dynamic perfect hashing; Feature hashing; Image (mathematics); Similarity (geometry); Pattern recognition (psychology); Universal hashing; Hash table; Computer vision; Double hashing","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":[0.0009104412,0.0005827611,0.000744269,0.0007665601,0.0003148306,0.0007586527,0.001704833,0.0007510337,0.003905871],"category_scores_gemma":[0.003149157,0.0002738561,0.0004436147,0.0007510125,0.0008600156,0.002130722,0.001599743,0.0009330213,0.001516414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005114271,"about_ca_system_score_gemma":0.0007043995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001040323,"about_ca_topic_score_gemma":0.001425396,"domain_scores_codex":[0.9994484,0.00009613286,0.00003662388,0.000114506,0.0002525181,0.0000519423],"domain_scores_gemma":[0.9992231,0.0001973646,0.00008592835,0.0002866697,0.0001618794,0.00004506411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006547402,0.000186758,0.001250272,0.0003807156,0.00008991905,0.0001418523,0.0001315273,0.05866715,0.05059033,0.02635971,0.008764926,0.8527822],"study_design_scores_gemma":[0.00007660742,0.0004125653,0.0008357448,0.0000343412,0.00003312422,0.0006345043,0.00006363571,0.9069768,0.06006701,0.01774261,0.01306144,0.00006157265],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01652939,0.000693606,0.9783686,0.0001065435,0.000129345,0.0001484336,0.000152017,0.002092513,0.001779551],"genre_scores_gemma":[0.4205773,0.0007899335,0.5692816,0.0002995927,0.0001404239,0.0002101144,0.0008701073,0.0002507982,0.007580098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003905871,"threshold_uncertainty_score":0.01306641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03838171986153987,"score_gpt":0.3489617861028698,"score_spread":0.3105800662413299,"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."}}