{"id":"W4407385589","doi":"10.3390/jimaging11020052","title":"SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Object (grammar); Embedding; Shot (pellet); Computer vision; Feature (linguistics); Class (philosophy); Pattern recognition (psychology); Zero (linguistics); Matching (statistics); Mathematics; Statistics","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":[0.002247034,0.0001235873,0.0002416299,0.0003596329,0.0002027313,0.0003162939,0.000408065,0.00002752397,0.000001094071],"category_scores_gemma":[0.0002975386,0.0001095405,0.0001886996,0.0004051077,0.00001253153,0.0006044077,0.00006939146,0.0002069546,0.000002344521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001168238,"about_ca_system_score_gemma":0.0001479488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000259162,"about_ca_topic_score_gemma":4.926154e-7,"domain_scores_codex":[0.9986958,0.0001177265,0.0004501592,0.000196022,0.0002737752,0.0002665244],"domain_scores_gemma":[0.998652,0.0003167863,0.0005202808,0.0001649938,0.0003018726,0.00004407916],"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":[0.0001047554,0.0003564854,0.08962622,0.0002939992,0.0003888922,0.0001564107,0.0009045482,0.002902634,0.09135647,0.008792382,0.008470042,0.7966471],"study_design_scores_gemma":[0.003529988,0.0004025509,0.09470382,0.001442132,0.0001512796,0.0004508024,0.0002506551,0.843838,0.02420345,0.01348015,0.01684531,0.0007018622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07381303,0.0003349609,0.9217699,0.001070781,0.002194701,0.00007800505,3.699006e-7,0.00005638471,0.0006819026],"genre_scores_gemma":[0.7866862,0.00002223072,0.212258,0.0007203488,0.000235249,0.000002257809,3.549979e-7,0.000009113779,0.00006626058],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8409353,"threshold_uncertainty_score":0.4466933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02050528559219349,"score_gpt":0.3571574866703086,"score_spread":0.3366522010781151,"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."}}