{"id":"W3207740618","doi":"10.1109/crv60082.2023.00031","title":"Multi-Object Tracking and Segmentation with a Space-Time Memory Network","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Segmentation; Computer vision; Video tracking; Association (psychology); Metric (unit); Object (grammar); Tracking (education); Object detection; Optical flow; Pattern recognition (psychology); Image (mathematics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001449254,0.00031261,0.0004080474,0.0001342097,0.0001517947,0.0005357676,0.0005220384,0.0001761356,0.00001075786],"category_scores_gemma":[0.00004740561,0.0002548911,0.00007352465,0.0003608426,0.00005059595,0.0002688024,0.0008488457,0.0004290334,0.00005657152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004287513,"about_ca_system_score_gemma":0.000123931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000192362,"about_ca_topic_score_gemma":0.0002213385,"domain_scores_codex":[0.9978288,0.0002942521,0.0002675571,0.0008981354,0.0003183206,0.0003929687],"domain_scores_gemma":[0.9985273,0.0003618234,0.000205039,0.0007170049,0.0000931768,0.00009559326],"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":[0.000119785,0.0002548489,0.06148195,0.001144976,0.001199163,0.0006874082,0.009866398,0.2584642,0.003134597,0.00197952,0.00665193,0.6550152],"study_design_scores_gemma":[0.002218701,0.0002830095,0.2420905,0.001174789,0.0001053197,0.0001127569,0.0001886809,0.7386601,0.003476675,0.009243999,0.0003497278,0.002095763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01244023,0.0002686411,0.9837946,0.0006674172,0.000722907,0.0004698382,0.000002994401,0.0009299377,0.0007033995],"genre_scores_gemma":[0.05042792,0.0001118909,0.9467306,0.0002006957,0.0002679036,0.00006058862,0.00001781862,0.00004574049,0.002136841],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6529195,"threshold_uncertainty_score":0.9999903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05288857456265991,"score_gpt":0.3089768751565303,"score_spread":0.2560883005938704,"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."}}