{"id":"W4417161975","doi":"10.1109/iccv51701.2025.00730","title":"TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feed forward; Leverage (statistics); Event (particle physics); ENCODE; Monocular; Discriminative model; Noise (video); Deep learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0000920709,0.0001415293,0.0001616213,0.0000616593,0.00009765569,0.00002004024,0.000116164,0.00004992454,0.00003319695],"category_scores_gemma":[0.00003832331,0.0001367948,0.00007035693,0.0001788768,0.000008214333,0.0001093745,0.00002599844,0.0001197972,0.000006855885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000489929,"about_ca_system_score_gemma":0.00001861209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.33778e-7,"about_ca_topic_score_gemma":0.000002677402,"domain_scores_codex":[0.9992816,0.000008944276,0.0002122609,0.0001819602,0.00005890613,0.0002562713],"domain_scores_gemma":[0.9996076,0.0001474869,0.00001591236,0.0001519065,0.00003385936,0.00004329039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000668067,0.00007802393,0.0002679778,0.0009241603,0.0002342793,0.000007399978,0.001572706,0.2623066,0.4904532,0.005443442,0.00433778,0.2343076],"study_design_scores_gemma":[0.0009565338,0.00006674758,0.0001020117,0.0001202148,0.00002341857,0.000001658342,0.0002935224,0.5138087,0.4772814,0.001371349,0.005641021,0.0003334441],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3151539,0.0001747535,0.6586021,0.00008824038,0.0005298626,0.0004465795,0.000002674046,0.001388676,0.02361323],"genre_scores_gemma":[0.9554986,0.0000106955,0.04279198,0.000201889,0.00008204279,0.00004163472,0.000004750538,0.00002147351,0.001346947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6403447,"threshold_uncertainty_score":0.5578331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00976999849713157,"score_gpt":0.2594428188344185,"score_spread":0.2496728203372869,"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."}}