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
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
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.86)
- VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention (AAAI 2025 · similarity 0.86)
- Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data (ICML 2026 · similarity 0.85)
- H-MoRe: Learning Human-centric Motion Representation for Action Analysis (CVPR 2025 · similarity 0.84)
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition (NeurIPS 2025 · similarity 0.84)
- Inertia-1: An Open Exploration of Wearable Motion Foundation Models (NeurIPS 2026 · similarity 0.83)
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.
