Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Evidential Deep Learning for Online Action Detection
Hongji Guo, Hanjing Wang, Qiang Ji
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| two-stage training instead of joint training (ablation) | BEDL · THUMOS'14 (ActivityNet) | mAP (%): 69.5 -> 70.6 | Improved |
| two-stage training instead of separate (frozen attention) training (ablation) | BEDL · TVSeries (ActivityNet) | mcAP (%): 81.6 -> 88.9 | Improved |
| add Bayesian mutual information attention module (ablation) | BEDL · THUMOS'14 (ActivityNet) | mAP (%): 63.1 -> 70.6 | Improved |
| use Bayesian MI instead of single-prediction MI (ablation) | BEDL attention module · THUMOS'14 (Kinetics) | mAP (%): 68.4 -> 72.7 | Improved |
| Laplace approximation over all parameters instead of last layer only (ablation) | Bayesian teacher · TVSeries (ActivityNet) | mcAP (%): 88.9 -> 90.2 | Improved |
| increase past frames from 64 to 128 (ablation) | BEDL · THUMOS'14 (ActivityNet) | mAP (%): 70.6 -> 66.5 | Hurt |
| increase past frames from 8 to 64 (ablation) | BEDL · THUMOS'14 (ActivityNet) | mAP (%): 41.6 -> 70.6 | Improved |
| use epistemic instead of aleatoric uncertainty for anomaly detection (ablation) | BEDL · THUMOS'14 anomaly detection | AUC (%): 62.51 -> 86.48 | Improved |
| Bayesian distribution distillation to evidential student vs plain EDL | uncertainty quantification · TVSeries anomaly detection | AUC (%): 42.39 -> 69.44 | Improved |
| BEDL as lightweight student model vs prior OAD models | BEDL · Efficiency | model FPS: 123.3 -> 163.2 | Improved |
Closest papers by meaning
- Uncertainty Estimation by Flexible Evidential Deep Learning (NeurIPS 2025 · similarity 0.87)
- Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? (NeurIPS 2024 · similarity 0.86)
- Towards Evidential and Class Separable Open Set Object Detection (AAAI 2024 · similarity 0.85)
- Uncertainty Estimation by Density Aware Evidential Deep Learning (ICML 2024 · similarity 0.84)
- The Evidence Contraction Issue in Deep Evidential Regression: Discussion and Solution (AAAI 2024 · similarity 0.84)
- Calibrating LLMs with Information-Theoretic Evidential Deep Learning (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
