AI Paper Atlas

Research map / Video / Action recognition

Unsupervised Learning and Segmentation of Complex Activities From Video

Fadime Sener, Angela Yao

CVPR 2018 · Video › Action recognition · approach: Temporal action segmentation · 116 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 the GMM temporal ordering model (ablation)the appearance model on Inria Instructional Videos without background · Inria Instructional Videos without backgroundMof: 0.322 -> 0.692Improved
use the fully unsupervised iterated methodBreakfast Actions · Breakfast ActionsMof: 33.3 -> 34.6Improved
use the fully unsupervised iterated methodBreakfast Actions · Breakfast ActionsJaccard: 47.3 -> 47.1No clear effect
increase rho_0 to 5 to encourage a stricter canonical orderingthe proposed GMM model · Inria Instructional Videos, change tireF1: 0.41 vs. 0.42No clear effect
use a few Gaussian mixture components for the visual appearance model (ablation)the proposed model · Inria Instructional Videos without backgroundMofImproved
vary the embedding dimensionality (ablation)the proposed model · Inria Instructional Videos without backgroundMofNo clear effect
account for background frames in the model (ablation)the standard model on Inria Instructional Videos · Inria Instructional VideosMofImproved
use the GMM ordering model on activities with repeated sub-activitiesthe proposed model · Inria Instructional Videos, perform CPRF1Hurt
increase the assumed number of sub-activities K (ablation)the proposed model · Inria Instructional Videos without backgroundMofNo clear effect

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