{"id":"W3140801471","doi":"10.48550/arxiv.2103.15368","title":"Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pixel; Computer science; Artificial intelligence; Computer vision; Compression (physics); Image compression; Layer (electronics); Sketch; Region of interest; Texture compression; Image (mathematics); Data compression; Pattern recognition (psychology); Image processing; Algorithm; Materials science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000184847,0.0004134999,0.0005770866,0.0002914325,0.0002066691,0.0001734121,0.001666986,0.0003431756,0.00003027857],"category_scores_gemma":[0.00008251058,0.0004983159,0.0002657827,0.000674092,0.0003398202,0.001252942,0.002362713,0.0006607479,0.000007294057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002244695,"about_ca_system_score_gemma":0.0001933072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001145098,"about_ca_topic_score_gemma":0.00000740113,"domain_scores_codex":[0.9972819,0.0002927897,0.0004748791,0.001404928,0.0001873692,0.0003581011],"domain_scores_gemma":[0.9964229,0.0001107477,0.001031646,0.001471536,0.0008217704,0.0001413463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001440631,0.001238348,0.006448723,0.002126483,0.0004806957,0.001139591,0.001385353,0.02412208,0.9033386,0.0187226,0.005316237,0.03553726],"study_design_scores_gemma":[0.000895502,0.00007218045,0.0005773702,0.001266551,0.00010564,0.00007610631,0.0002392449,0.8705702,0.08549538,0.03964307,0.00009553457,0.0009631679],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1507646,0.0002124885,0.8468004,0.00005324939,0.0004261973,0.0002870605,0.00001734988,0.0004939449,0.0009447009],"genre_scores_gemma":[0.7630029,0.0002547903,0.2363342,0.00003337318,0.00002592183,0.000002054472,0.00006675649,0.00002471899,0.0002552301],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8464482,"threshold_uncertainty_score":0.9997469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03678798240684051,"score_gpt":0.2124397920278076,"score_spread":0.1756518096209671,"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."}}