{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003430082,0.0002125218,0.0002126762,0.0002661741,0.0007267785,0.0004323607,0.0003197617,0.00007289544,0.00001217249],"category_scores_gemma":[0.00002861995,0.0002178323,0.00007794482,0.000729112,0.0001137396,0.002715683,0.00001394143,0.0003670368,0.000007891493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006825146,"about_ca_system_score_gemma":0.0003492117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004006157,"about_ca_topic_score_gemma":0.00002369489,"domain_scores_codex":[0.9984388,0.00005307924,0.0003237542,0.000610608,0.000255808,0.0003179873],"domain_scores_gemma":[0.999103,0.00007808662,0.00009290991,0.0004043921,0.0001909405,0.0001307435],"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":[0.0001663996,0.0007275817,0.00002380542,0.0004468914,0.00005047951,0.00001875752,0.00178963,0.001322445,0.2075526,0.00222566,0.001840036,0.7838356],"study_design_scores_gemma":[0.0008967026,0.00004581541,0.00006979579,0.0002972094,0.00003813392,0.00002719778,0.0001181046,0.5468966,0.4328808,0.01752183,0.0007846917,0.0004231462],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004431381,0.0003170048,0.9958588,0.0008789335,0.0001135486,0.0001802265,0.00002853695,0.0006519865,0.001527859],"genre_scores_gemma":[0.1715917,0.0001195792,0.8250223,0.000664003,0.00002784691,0.00004126022,0.000003037952,0.00001658845,0.002513646],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7834125,"threshold_uncertainty_score":0.8882945,"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."}}