AI Paper Atlas

Research map / Video / Action recognition

When a Window Is Not an Action: Selective Phase-Script Deliberation for Sliding-Window Human Activity Recognition

Qi Teng, Xueer Wang

NeurIPS 2026 · Video › Action recognition · approach: Disentangled action recognition

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes selective phase-script deliberation for sliding-window human activity recognition, targeting windows that do not align with a single activity action.

Problem

Sliding-window HAR assigns one label per fixed-length window, but windows often do not align with motion cycles or activity changes, so some windows contain partial, transitional, or mixed motion that a single label misrepresents.

Approach

Selectively applies phase-script deliberation to windows that are not cleanly a single action, rather than classifying every window the same way; the abstract gives no further method detail.

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