AI Paper Atlas

Research map / Video / Action recognition

Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions

Zhi Li, Lu He, Huijuan Xu

ECCV 2022 · Video › Action recognition · approach: Temporal action segmentation · 12 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 pseudo-label self-supervised clustering loss (ablation)HAAN · FineAction valavg mAP: 2.72 -> 3.18Improved
add visual concept loss (ablation)HAAN · FineAction valavg mAP: 3.18 -> 3.57Improved
add coarse-level label hierarchy loss (ablation)HAAN · FineAction valavg mAP: 3.57 -> 4.10Improved
add pseudo-label loss (ablation)HAAN · FineGym-99 (new split)avg mAP: 5.61 -> 6.09Improved
add visual concept loss (ablation)HAAN · FineGym-99 (new split)avg mAP: 6.09 -> 6.95Improved
add coarse-level label hierarchy loss (ablation)HAAN · FineGym-99 (new split)avg mAP: 6.95 -> 7.67Improved
use cosine instead of Euclidean distance (ablation)HAAN · FineAction valavg mAP: 3.26 -> 3.57Improved
use K-means instead of GMM clustering (500 clusters) (ablation)HAAN · FineAction valmAP@0.5: 6.14 -> 6.40Improved
use K-means instead of Birch clustering (500 clusters) (ablation)HAAN · FineAction valmAP@0.5: 6.31 -> 6.40Improved
vary number of K-means clusters from 250 to 1000 (ablation)HAAN · FineAction valmAP@0.5: 6.31, 6.40, 6.25, 6.26No clear effect
HAAN vs best weakly-supervised baseline WTAL-UMHAAN · FineAction valavg mAP: 3.64 -> 4.10Improved
HAAN vs best weakly-supervised baseline WTAL-UMHAAN · FineGym-99 (new split)avg mAP: 6.11 -> 7.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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