{"id":"W4412444826","doi":"10.1109/tip.2025.3583181","title":"Perceptual Quality Assessment of 360° Images Based on Generative Scanpath Representation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Innovation and Technology Fund; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Representation (politics); Perception; Computer vision; Image quality; Generative model; Quality (philosophy); Quality assessment; Image processing; Generative grammar; Image (mathematics)","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":[0.000384473,0.0001589025,0.0001979889,0.0003747247,0.0003968221,0.0002057728,0.0002565764,0.0000594595,0.00003755721],"category_scores_gemma":[0.00001631925,0.0001519737,0.0001271568,0.000856892,0.00009981008,0.0007012069,0.000002869384,0.0002281384,0.000006383375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001299306,"about_ca_system_score_gemma":0.0002376433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003479291,"about_ca_topic_score_gemma":0.00001178671,"domain_scores_codex":[0.9982687,0.00025926,0.00040287,0.0004732715,0.0004235203,0.0001723896],"domain_scores_gemma":[0.9990472,0.00009554202,0.0001605288,0.0003500202,0.0002994092,0.00004733993],"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":[0.00009404062,0.001453446,0.000201044,0.0002558524,0.00003990574,0.000004485348,0.0009791933,0.03334635,0.3751134,0.001085976,0.0001537179,0.5872726],"study_design_scores_gemma":[0.0006430898,0.0001933674,0.005600831,0.000141468,0.00002077218,0.000001248128,0.0003218675,0.603597,0.3889506,0.0003430306,0.00001499087,0.0001717159],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01278326,0.000009130373,0.9823461,0.0008915179,0.0003992424,0.0001934279,0.000009626551,0.0001671659,0.003200495],"genre_scores_gemma":[0.9349145,0.000004178553,0.06411128,0.0003740159,0.00001417344,0.00005010915,0.000002191724,0.000007523539,0.0005220235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9221312,"threshold_uncertainty_score":0.6197308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04266333309886469,"score_gpt":0.3893710332024057,"score_spread":0.3467077001035411,"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."}}