{"id":"W3134101093","doi":"10.1109/tmm.2021.3062481","title":"AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Manitoba; Huawei Technologies (Canada); Simon Fraser University","funders":"University of Manitoba","keywords":"Computer science; Artificial intelligence; Benchmark (surveying); Adaptation (eye); Computer vision; Code (set theory); Counting problem; Image (mathematics); Pattern recognition (psychology); Algorithm","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":[0.0005016342,0.0001657664,0.0002077312,0.0001116603,0.0002900104,0.0001450806,0.0002853707,0.0001014352,0.00003418809],"category_scores_gemma":[0.00006902419,0.0001759386,0.0001486081,0.0004932529,0.00003236818,0.0003970681,0.000001976951,0.0001963139,0.00005550571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005404752,"about_ca_system_score_gemma":0.0001826362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002843701,"about_ca_topic_score_gemma":0.0001545345,"domain_scores_codex":[0.9985285,0.0001257986,0.0002778636,0.0004673477,0.0002688854,0.0003315813],"domain_scores_gemma":[0.9982591,0.0007983777,0.00008122638,0.0004532918,0.0003133902,0.00009462578],"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":[0.00003565458,0.0002564578,0.00004508305,0.00004219027,0.00007561299,0.00002203528,0.00111003,0.02268637,0.02020073,0.000201411,0.0001932128,0.9551312],"study_design_scores_gemma":[0.001422432,0.00008217379,0.0005578957,0.00004891163,0.00002469614,0.0000179621,0.00008428946,0.7527257,0.2417458,0.0004511044,0.002540653,0.0002983991],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004796627,0.00008864462,0.992008,0.0005885094,0.001891394,0.0002101129,0.0000232116,0.0002485388,0.0001449201],"genre_scores_gemma":[0.493609,0.00003028164,0.5055782,0.0002733597,0.00008213482,0.00006504386,0.000006196335,0.0000170551,0.0003386792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9548328,"threshold_uncertainty_score":0.7174566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04566899353662336,"score_gpt":0.3040500184347916,"score_spread":0.2583810248981683,"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."}}