{"id":"W7117101366","doi":"10.1109/tnse.2025.3647916","title":"GenAI-Enabled Residual Motion Estimation for Energy-Efficient Semantic Video Communication","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Residual; Bandwidth (computing); Convolutional neural network; Motion estimation; Semantic similarity; Video tracking; Semantics (computer science); Channel (broadcasting)","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","sts"],"consensus_categories":[],"category_scores_codex":[0.001402677,0.0003111649,0.0002913652,0.0007556321,0.00209934,0.0007009045,0.001126437,0.0001835246,0.000002637625],"category_scores_gemma":[0.00008139919,0.0003214381,0.00008539704,0.002984815,0.0003288919,0.0006434353,0.00003743861,0.0003497679,0.000002696025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002374761,"about_ca_system_score_gemma":0.0002835434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003321782,"about_ca_topic_score_gemma":0.0000081179,"domain_scores_codex":[0.9974806,0.00004863053,0.0004878257,0.0007765259,0.0005015162,0.0007048777],"domain_scores_gemma":[0.9980718,0.0003806368,0.0001243035,0.0009722924,0.000334962,0.0001159776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001413629,0.000055137,0.000001086643,0.00007766023,0.00001614662,4.019499e-7,0.0001235925,0.7741928,0.001142475,0.009850492,0.0003454707,0.2141806],"study_design_scores_gemma":[0.0003831991,0.0001097394,0.000091138,0.0009281381,0.00005204634,0.000005496544,0.00004671491,0.9746068,0.02176635,0.001181068,0.0005422567,0.0002871194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008070788,0.001335143,0.9861383,0.001567492,0.001925788,0.000380335,0.000003606546,0.000491518,0.00008700393],"genre_scores_gemma":[0.9666349,0.0007540347,0.03201113,0.0001280902,0.00004383253,0.0001726265,0.000001014855,0.00001367251,0.0002406742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9585642,"threshold_uncertainty_score":0.9999238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01220072395907836,"score_gpt":0.2324917146638968,"score_spread":0.2202909907048184,"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."}}