{"id":"W4414596608","doi":"10.1007/s11554-025-01761-4","title":"WT-DETR: Wavelet-enhanced DETR for robust tiny object detection via multi-scale feature optimization","year":2025,"lang":"en","type":"article","venue":"Journal of Real-Time Image Processing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Chongqing","keywords":"Upsampling; Aliasing; Wavelet; Feature (linguistics); Context (archaeology); Convolution (computer science); Object detection; Field (mathematics); Representation (politics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006630408,0.0009838007,0.001017037,0.0007665141,0.0003540137,0.0006601234,0.0009777742,0.0008036359,0.003906536],"category_scores_gemma":[0.001335354,0.0003895266,0.0008307429,0.0007919204,0.0003279743,0.0008069875,0.001294922,0.001180121,0.00231129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002049746,"about_ca_system_score_gemma":0.0005309752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001560423,"about_ca_topic_score_gemma":0.002852963,"domain_scores_codex":[0.9996816,0.00003413475,0.00001617358,0.0000578941,0.000179891,0.00003025738],"domain_scores_gemma":[0.999688,0.00007130914,0.00003008517,0.00007040353,0.0001159736,0.00002428435],"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":[0.0005130698,0.0002248565,0.001032765,0.0001916873,0.0001623821,0.0002351071,0.00005767265,0.05301727,0.08782701,0.005264708,0.01600166,0.8354718],"study_design_scores_gemma":[0.00001496959,0.0000782549,0.0008166548,0.000008021575,0.00001786849,0.0001531962,0.00001191745,0.9664336,0.02431273,0.002033,0.00609783,0.00002191073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005824134,0.0001557745,0.9901468,0.0000850829,0.00007481613,0.00003653198,0.0002162444,0.002820113,0.0006405652],"genre_scores_gemma":[0.1140002,0.0002738511,0.873194,0.0002244658,0.0001034588,0.0001662639,0.002058697,0.001057225,0.008921782],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003906536,"threshold_uncertainty_score":0.01306868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051958058838433,"score_gpt":0.2766373403406846,"score_spread":0.2661177597523003,"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."}}