AI Paper Atlas

Research map / Video / Action recognition

Recognizing Complex Activities by a Probabilistic Interval-Based Model

Li Liu, Li Cheng, Ye Liu, Yongpo Jia, David Rosenblum

AAAI 2016 · Video › Action recognition · approach: Disentangled action recognition · 204 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
interval-based model with CRP latent tables (GPA) instead of ITBNcomplex activity recognition · CAD14accuracy: 0.51 -> 0.97Improved
GPA instead of ITBNcomplex activity recognition · OSUPELaccuracy: 0.69 -> 0.79Improved
GPA instead of ITBN under real detected atomic errorscomplex activity recognition · Opportunity, DT errorsaccuracy: 0.38 -> 0.71Improved
use fully connected interval links (GPA-F) instead of chain (ablation)GPA · OSUPEL/Opportunity/CAD14accuracy: 0.79 -> 0.76 (OSUPEL); 0.97 -> 0.98 (CAD14)Mixed
use fully connected interval links (GPA-F) (ablation)GPA · Opportunity, real detected errorsaccuracy: 0.91 -> 0.79 (kNN)Hurt

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