{"id":"W4407782160","doi":"10.1109/tip.2025.3539468","title":"Omnidirectional Image Quality Captioning: A Large-Scale Database and a New Model","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Scale (ratio); Closed captioning; Artificial intelligence; Database; Computer vision; Image processing; Image quality; Omnidirectional antenna; Quality (philosophy); Image (mathematics); Data mining; Pattern recognition (psychology); Information retrieval","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":[0.002507097,0.001012515,0.001087304,0.002208328,0.0004555082,0.002064165,0.003143732,0.001179725,0.00363552],"category_scores_gemma":[0.009495198,0.0004829151,0.0008509135,0.002639389,0.0006788041,0.002868615,0.00196851,0.001398918,0.002568408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118343,"about_ca_system_score_gemma":0.0008104796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007411358,"about_ca_topic_score_gemma":0.006090203,"domain_scores_codex":[0.9979449,0.0003963,0.0001624264,0.0005800854,0.0008077256,0.0001085434],"domain_scores_gemma":[0.9953967,0.0007961228,0.0002971852,0.001719052,0.001585379,0.0002055435],"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":[0.001306136,0.0007936159,0.005461749,0.001065677,0.000180606,0.0005754901,0.0003022724,0.105808,0.03123716,0.01272126,0.0533005,0.7872476],"study_design_scores_gemma":[0.00008395827,0.0003385478,0.005497338,0.00008746338,0.00009663484,0.0008775125,0.0001778248,0.9385395,0.01656222,0.007746898,0.029872,0.0001200924],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03738341,0.003123695,0.935715,0.0008211972,0.0002778212,0.001146735,0.008551727,0.006356113,0.006624233],"genre_scores_gemma":[0.3821371,0.003393278,0.5716544,0.0005907767,0.0002794951,0.001495996,0.03226022,0.0005604714,0.007628207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007411358,"threshold_uncertainty_score":0.01473641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03364558869461897,"score_gpt":0.3468165080732853,"score_spread":0.3131709193786663,"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."}}