{"id":"W4392902789","doi":"10.1109/icassp48485.2024.10447420","title":"Efficient Learned Image Compression with Selective Kernel Residual Module and Channel-Wise Causal Context Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Google","keywords":"Computer science; Residual; Decoding methods; Encoding (memory); Kernel (algebra); Data compression; Image compression; Context (archaeology); Distortion (music); Artificial intelligence; Compression (physics); Algorithm; Rate–distortion theory; Image (mathematics); Pattern recognition (psychology); Theoretical computer science; Image processing; Mathematics; Bandwidth (computing)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002366456,0.0005304489,0.00047292,0.0004033629,0.0001723034,0.0002946204,0.0008810507,0.0004183851,0.001092276],"category_scores_gemma":[0.0007423476,0.0001593875,0.0003325751,0.0004702552,0.000328557,0.0009504239,0.0006222397,0.0005944493,0.0002666927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000315356,"about_ca_system_score_gemma":0.0005834341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002823574,"about_ca_topic_score_gemma":0.003396349,"domain_scores_codex":[0.9998237,0.00003100754,0.000008194664,0.0000350866,0.00007583109,0.00002610087],"domain_scores_gemma":[0.9998196,0.00004337862,0.00002305399,0.00003774202,0.00006162083,0.00001470052],"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":[0.000304267,0.0001583366,0.0009205187,0.0001496623,0.00007545121,0.000238697,0.0001080551,0.3361109,0.08278207,0.01963393,0.003558101,0.5559601],"study_design_scores_gemma":[0.000007314315,0.00003501305,0.0001426938,0.000003796321,0.00001052795,0.00006136986,0.000005876583,0.9868989,0.01083533,0.001330901,0.0006610409,0.000007229051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04388517,0.0005256937,0.9526459,0.0001161906,0.00003893361,0.00004348211,0.00006344475,0.0009506803,0.001730585],"genre_scores_gemma":[0.72299,0.0006126308,0.2711216,0.0001986946,0.0000794793,0.0001084667,0.0003244995,0.0001260919,0.004438615],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002823574,"threshold_uncertainty_score":0.00561434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01848326567702807,"score_gpt":0.2827288535105807,"score_spread":0.2642455878335526,"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."}}