{"id":"W4404820184","doi":"10.1007/978-3-031-72848-8_19","title":"VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Computer science; Shot (pellet); Zero (linguistics); Asset (computer security); Image (mathematics); Computer vision; Diffusion; Artificial intelligence; Computer security; Physics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001269503,0.0004325208,0.0004377509,0.001040546,0.0002213003,0.001152232,0.0013545,0.0002400887,0.00001109184],"category_scores_gemma":[0.0002624396,0.0004136169,0.00007266193,0.0005464919,0.0002920935,0.0008669274,0.001430061,0.0006055002,0.00001546838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000388152,"about_ca_system_score_gemma":0.0002094198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003766171,"about_ca_topic_score_gemma":0.0001005075,"domain_scores_codex":[0.9963654,0.00003976827,0.0006519595,0.001628975,0.0007360202,0.0005778694],"domain_scores_gemma":[0.9982482,0.0004972555,0.0001879913,0.000680989,0.0001636211,0.0002219673],"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":[0.000003177412,0.00003232878,0.00004581148,0.0001146475,0.000005812143,0.00007896307,0.00242079,0.001359475,0.06122161,0.003199223,0.0001244719,0.9313937],"study_design_scores_gemma":[0.000242472,0.0001915903,0.0001134283,0.0006050927,0.000006837704,0.00002679565,6.859032e-7,0.9284033,0.03100184,0.03857839,0.000297962,0.000531581],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002711857,0.0001648256,0.9934729,0.001299242,0.0008626169,0.0008896277,0.000007048448,0.0002879446,0.0003039851],"genre_scores_gemma":[0.06652574,0.00002995683,0.9305288,0.002185441,0.0003871493,0.00008284443,0.00001913994,0.00004442064,0.0001964766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9308621,"threshold_uncertainty_score":0.9998847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02722686866305506,"score_gpt":0.291987410812122,"score_spread":0.264760542149067,"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."}}