AI Paper Atlas

Research map / Video / Action recognition

Refining Action Segmentation With Hierarchical Video Representations

Hyemin Ahn, Dongheui Lee

ICCV 2021 · Video › Action recognition · approach: Temporal action segmentation · 77 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 HASR refinementMS-TCN · 50SaladsEdit score: 70.4 -> 77.4Improved
add HASR refinementASRF · 50SaladsEdit score: 79.9 -> 81.0Improved
add HASR refinementSSTDA · 50SaladsEdit score: 74.9 -> 77.3Improved
add HASR refinementGRU · BreakfastEdit score: 32.3 -> 61.2Improved
add HASR refinementMS-TCN · BreakfastEdit score: 66.2 -> 70.8Improved
add HASR refinementSSTDA · BreakfastEdit score: 70.2 -> 70.0No clear effect
add HASR refinementSSTDA · GTEAEdit score: 87.9 -> 87.5No clear effect
add HASR refinementMS-TCN · GTEAFrame accuracy: 78.3 -> 77.4Hurt
refine backbone with HASR trained on other backbones (unseen)GRU · BreakfastEdit score: 32.3 -> 53.0Improved
add segment-level representation (ablation)HASR · 50SaladsEdit score: 72.3 -> 77.4Improved
add video-level representation (ablation)HASR · 50SaladsEdit score: 74.9 -> 77.4Improved
use sample-based residual blocks instead of GRU for video-level encoder (ablation)HASR · 50SaladsEdit score: 76.7 -> 77.4Improved

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