{"id":"W4402904107","doi":"10.1109/cvprw63382.2024.00708","title":"TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Closed captioning; Computer science; Speech recognition; Artificial intelligence; 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":[0.0002912615,0.0001270172,0.0001361125,0.0001234197,0.0001522305,0.0004177384,0.0003998641,0.00005414291,0.0000263907],"category_scores_gemma":[0.00004884139,0.0001123156,0.0001001823,0.0003130034,0.00001845541,0.0003032845,0.00005603235,0.00014185,0.0001588453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004728443,"about_ca_system_score_gemma":0.0001077945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007678003,"about_ca_topic_score_gemma":0.00003792781,"domain_scores_codex":[0.9989166,0.00002337951,0.0001888882,0.0004480639,0.0001511309,0.0002718873],"domain_scores_gemma":[0.9992999,0.00026067,0.00002566951,0.0002859521,0.00004489794,0.00008285495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005726757,0.00005461184,0.000004538693,0.00004141191,0.00002677212,0.000003084504,0.002924503,0.763625,0.004547379,0.121121,0.001772615,0.1058733],"study_design_scores_gemma":[0.000311069,0.00003454724,0.00002665872,0.00001493978,0.00001011316,0.000006567515,0.00004389389,0.9978584,0.0001402019,0.0004703124,0.0009393001,0.0001440034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09366612,0.0002709993,0.900588,0.002332674,0.0001009463,0.0003733252,0.000005170576,0.001418792,0.001243969],"genre_scores_gemma":[0.8636658,0.000001583076,0.1326328,0.0002396088,0.00007799504,0.000231515,0.000008581335,0.00001849799,0.003123667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7699996,"threshold_uncertainty_score":0.4580096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01249358995875663,"score_gpt":0.3133651745960067,"score_spread":0.3008715846372501,"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."}}