AI Paper Atlas

Research map / Video / Action recognition

Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization

Mengyuan Chen, Junyu Gao, Changsheng Xu

CVPR 2023 · Video › Action recognition · approach: Weakly supervised temporal action localization · 21 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use CELL instead of ARPL for open-world localizationCO2-Net · THUMOS-14mAP@Avg (%): 29.2 -> 32.3Improved
Use CELL instead of EDL for open-world localizationASM-Loc · ActivityNet-v1.3mAP@Avg (%): 17.0 -> 18.9Improved
Add multi-scale extended-range perception (MEP) (ablation)CELL · THUMOS-14mAP@Avg (%): 27.8 -> 29.0Improved
Add knowledge-guided bipolar prototype learning (KBPL) (ablation)CELL · THUMOS-14mAP@Avg (%): 27.8 -> 29.2Improved
Add MEP and KBPL together (ablation)CELL · THUMOS-14mAP@Avg (%): 27.8 -> 31.6Improved
Add the uncertainty-aware adaptor (UA) (ablation)CELL with MEP and KBPL · THUMOS-14mAP@Avg (%): 31.6 -> 32.3Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy