{"id":"W2138383645","doi":"10.1109/icassp.1994.389489","title":"Intensity scale invariant motion estimation with rotation and spatial scaling information","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Motion estimation; Optical flow; Resampling; Image scaling; Affine transformation; Computer vision; Artificial intelligence; Interpolation (computer graphics); Structure from motion; Mathematics; Motion interpolation; Computer science; Motion field; Invariant (physics); Motion (physics); Quarter-pixel motion; Rotation (mathematics); Transformation (genetics); Scaling; Block-matching algorithm; Image (mathematics); Image processing; Geometry","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":[0.00009391388,0.00006165415,0.00006030794,0.00008203452,0.000115054,0.0001800812,0.00007058131,0.00001844803,0.00001533356],"category_scores_gemma":[0.00003178309,0.00004882733,0.000007684613,0.0001503709,0.00001960976,0.003213691,0.0000491948,0.00005364713,0.00003854823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002057372,"about_ca_system_score_gemma":0.000003786275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007072587,"about_ca_topic_score_gemma":0.0000112025,"domain_scores_codex":[0.9995082,0.00001307629,0.0001315765,0.0001138275,0.0001454216,0.00008790479],"domain_scores_gemma":[0.9996524,0.00001399757,0.00006645291,0.0001208613,0.000103332,0.00004299274],"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":[0.000003671252,0.000009302024,0.0005397167,0.000005441788,0.00000110573,3.973419e-7,0.0008358984,0.001498817,0.0001138503,0.001252108,0.00003980729,0.9956999],"study_design_scores_gemma":[0.0002546654,0.00002976734,0.01104286,0.00001849315,0.000001716034,0.000022809,0.00006180848,0.9865847,0.00107886,0.0007702416,0.00006126177,0.00007279054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01146233,0.000004585949,0.9862397,0.0007925243,0.00005683457,0.0001024156,1.93216e-7,0.0001203933,0.001220963],"genre_scores_gemma":[0.6848311,0.000003538838,0.3148062,0.0003270363,0.000007408541,0.000002081793,0.000002982009,0.00000142241,0.00001815605],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9956271,"threshold_uncertainty_score":0.2329848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051985687029132,"score_gpt":0.2159898052856757,"score_spread":0.2054699484153844,"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."}}