AI Paper Atlas

Research map / Video / Action recognition

Learning Probabilistic Embeddings for Unsupervised Action Segmentation

Shuai Li, Duc Vu, Juergen Gall

ECCV 2026 · Video › Action recognition · approach: Temporal action segmentation · 1 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 probabilistic embeddings to ASOTASOT · BreakfastMoF: 56.4 -> 60.7Improved
add probabilistic embeddings to ASOTASOT · Desktop AssemblyMoF: 59.0 -> 71.2Improved
add probabilistic embeddings to VASOTVASOT · Desktop AssemblyMoF: 67.9 -> 71.1Improved
add probabilistic embeddings to VASOTVASOT · 50Salads (Eval)MoF: 53.4 -> 62.2Improved
add probabilistic embedding (with MLP) to ASOT without GCN (ablation)ASOT · BreakfastF1: 35.7 -> 34.9Hurt
add probabilistic embedding (with MLP) to ASOT without GCN (ablation)ASOT · BreakfastMoF: 56.4 -> 59.2Improved
add GCN to probabilistic embedding (ablation)PEOT · BreakfastF1: 34.9 -> 40.5Improved
add probabilistic embedding to GCN (ablation)PEOT · Desktop AssemblyMoF: 63.8 -> 71.2Improved
add probabilistic embedding to GCN (ablation)PEOT · 50Salads (Eval)MoF: 50.4 -> 64.9Improved
use GCN instead of TCN (ablation)PEOT · BreakfastF1: 38.9 -> 40.5Improved
use weighted adjacency instead of unweighted (ablation)PEOT · BreakfastMoF: 59.5 -> 60.7Improved
connect 3 frames instead of 5 (ablation)PEOT · BreakfastMoF: 58.9 -> 60.7Improved

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