AI Paper Atlas

Research map / Video / Action recognition

Leveraging Action Affinity and Continuity for Semi-Supervised Temporal Action Segmentation

Guodong Ding, Angela Yao

ECCV 2022 · Video › Action recognition · approach: Temporal action segmentation · 22 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 affinity and continuity losses plus ABS on unlabelled videosMS-TCN base · 50Salads (5% labelled)frame accuracy: 28.1 -> 52.3Improved
add naive pseudo-labelling on unlabelled videosMS-TCN base · 50Salads (5% labelled)frame accuracy: 28.1 -> 24.0Hurt
add naive pseudo-labelling on unlabelled videosMS-TCN base · 50Salads (10% labelled)frame accuracy: 32.0 -> 41.1Improved
use action affinity loss with entropy loss instead of pseudo-labelling (ablation)semi-supervised MS-TCN · BreakfastF1 and accuracy: around 2%Improved
restrict anchor search to videos with the same activity label (ablation)affinity loss · Breakfast (5% labelled)frame accuracy: 38.1 -> 56.6Improved
increase sub-sampling stride from 20 to 60 (ablation)action continuity loss · Breakfast (10% labelled)frame accuracy: 49.5 -> 45.6Hurt
increase affinity loss weight alpha from 0.001 to 0.1 (ablation)semi-supervised MS-TCN · GTEA (10% labelled)frame accuracy: 58.0 -> 62.6Improved
raise continuity loss weight beta from 0.01 to 1 (ablation)semi-supervised MS-TCN · GTEA (10% labelled)frame accuracy: 62.6 -> 59.3Hurt
add ABS with v=0.05 over one-hot boundaries (ablation)semi-supervised MS-TCN · Breakfast (10% labelled)F1@10: 53.8 -> 56.9Improved
use fixed-duration linear smoothing instead of one-hot (ablation)semi-supervised MS-TCN · Breakfast (10% labelled)frame accuracy: 49.2 -> 49.1No clear effect
double vicinity from v=0.05 to 0.1 (ablation)ABS · Breakfast (10% labelled)frame accuracy: 49.5 -> 48.9Hurt
add ABS to fully-supervised MS-TCNMS-TCN · Breakfast (fully supervised)frame accuracy: 65.1 -> 68.9Improved

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