AI Paper Atlas

Research map / Video / Action recognition

Bottom-Up Temporal Action Localization with Mutual Regularization

Peisen Zhao, Lingxi Xie, Chen Ju, Ya Zhang, Yanfeng Wang, Qi Tian

ECCV 2020 · Video › Action recognition · approach: Weakly supervised temporal action localization · 187 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
add IntraC and InterC consistency losses to the baseline (ablation)bottom-up TAL baseline · THUMOS14 proposalsAR@50 (%): 39.02 -> 42.63Improved
add IntraC on all three phases (ablation)baseline · THUMOS14 proposalsAR@50 (%): 39.02 -> 41.91Improved
add IntraC on the continuing phase only (ablation)baseline · THUMOS14 proposalsAR@50 (%): 39.02 -> 40.46Improved
add IntraC on start and end phases only (ablation)baseline · THUMOS14 proposalsAR@50 (%): 39.02 -> 40.86Improved
add InterC on both continue-start and continue-end (ablation)baseline · THUMOS14 proposalsAR@50 (%): 39.02 -> 41.23Improved
add InterC on only one of continue-start or continue-end (ablation)baseline · THUMOS14 proposalsAR@50 (%): 39.02 -> 40.21 (C&S), 40.64 (C&E)Improved
add InterC on top of IntraC (ablation)IntraC model · THUMOS14 proposalsAR@50 (%): 41.91 -> 42.63Improved
add a proposal evaluation network score to start-end probability product (ablation)proposal ranking · THUMOS14 proposalsAR@50 (%): 42.63 -> 44.23Improved
increase BaseNet kernel size from 3 to 9 (2 layers) (ablation)BaseNet · THUMOS14 proposalsAR@50 (%): 39.54 -> 42.63; 11: 42.48, 13: 42.17Mixed
increase BaseNet depth from 2 to 5 layers (kernel 5) (ablation)BaseNet · THUMOS14 proposalsAR@50 (%): 40.98 -> 41.56 (3 layers), 41.68 (4), 40.98 (5)No clear effect
add IntraC and InterC to TSA-Net-small (reimplemented)TSA-Net-small · THUMOS14 proposalsAR@50 (%): 38.32 -> 39.73Improved
add IntraC and InterC to TSA-Net-large (reimplemented)TSA-Net-large · THUMOS14 proposalsAR@50 (%): 37.91 -> 39.68Improved

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