{"id":"W4408712297","doi":"10.1109/itsc58415.2024.10919958","title":"Pedestrian Crossing Intent Prediction Using Vision Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Pedestrian; Computer science; Transformer; Artificial intelligence; Computer vision; Transport engineering; Engineering; Electrical engineering; Voltage","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006575034,0.00009137881,0.00008937709,0.0001241648,0.0001937486,0.001126044,0.0001817521,0.00004737822,0.00001651471],"category_scores_gemma":[0.00001650855,0.00007263458,0.00008063189,0.0004310118,0.00004059999,0.0009345346,0.00003385318,0.0001198801,0.00001997003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000597335,"about_ca_system_score_gemma":0.0001078739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007323903,"about_ca_topic_score_gemma":0.00001249639,"domain_scores_codex":[0.9990682,0.00005816477,0.0001823306,0.000305983,0.0001869192,0.0001983737],"domain_scores_gemma":[0.9996635,0.00007155329,0.00001464736,0.0001636955,0.00003033606,0.0000562936],"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":[0.000004931283,0.00002110043,0.001021246,0.00006798017,0.00002222763,0.00003225358,0.00102252,0.0005751869,0.01261267,0.005691376,0.0001912233,0.9787373],"study_design_scores_gemma":[0.0001543788,0.00008861961,0.003894493,0.0001711855,0.000008123368,0.00007914438,0.00004819224,0.9746481,0.005599892,0.002420482,0.01273333,0.0001541222],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04497563,0.0002974547,0.9494024,0.0004853498,0.001512953,0.00006985924,0.000001233799,0.0005173053,0.002737837],"genre_scores_gemma":[0.9053134,0.00002013721,0.09434419,0.00007607294,0.0001008932,0.000001566463,0.000001152093,0.000008082732,0.0001345545],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9785832,"threshold_uncertainty_score":0.9999109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04660567227130682,"score_gpt":0.3537825785170712,"score_spread":0.3071769062457644,"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."}}