{"id":"W1980201039","doi":"10.1109/icip.2006.312920","title":"An FPGA-Based Implementation of Spatio-Temporal Object Segmentation","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Field-programmable gate array; Computer science; Modular design; Segmentation; Scalability; Virtex; Frame rate; Frame (networking); Computer hardware; Object (grammar); Embedded system; Image segmentation; Reconfigurable computing; Computer vision; Artificial intelligence","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":[0.000142225,0.00007595449,0.00008322476,0.00009724918,0.00004188218,0.00004572412,0.0002168807,0.00002162578,0.00007018019],"category_scores_gemma":[0.000002929514,0.0000690269,0.00003224848,0.0002730144,0.0000175922,0.0009473191,0.00002045358,0.0000279256,0.000003463268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003240191,"about_ca_system_score_gemma":0.00005384153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001037377,"about_ca_topic_score_gemma":0.000321353,"domain_scores_codex":[0.9992393,0.00003879492,0.0002330562,0.0001824912,0.0001932233,0.0001131835],"domain_scores_gemma":[0.9994819,0.0000208375,0.000125816,0.0002508663,0.00009697757,0.00002364313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003666213,0.0003702966,0.08770732,0.00005912682,0.00001146144,0.000009313853,0.0002976177,0.0006584504,0.1539495,0.03905207,0.003068923,0.7147793],"study_design_scores_gemma":[0.0002840386,0.0002470822,0.01132662,0.000003619926,0.000002457983,6.082016e-7,0.00004646906,0.005019352,0.977613,0.00505743,0.000308812,0.00009049592],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04862615,0.00001257246,0.9503884,0.00008091141,0.00002892213,0.0001848064,0.000003203676,0.000225248,0.0004498088],"genre_scores_gemma":[0.6751586,0.000001076247,0.3246341,0.00009123738,0.00001676783,0.000008227585,0.00006177344,0.000003516179,0.0000246212],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8236635,"threshold_uncertainty_score":0.2814835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376878493211351,"score_gpt":0.3299919604473935,"score_spread":0.31622317551528,"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."}}