OrganicHAR discovers 4-8 activity categories per user from sensor signals, achieves 79% accuracy on coarse activities with ambient sensors alone and cuts VLM queries by 90% by triggering video analysis only at detected pattern moments.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LastAct creates layout-aligned trajectory images from sensor events and applies boundary-guided masking to improve Macro-F1 on mixed sliding windows in smart-home HAR.
citing papers explorer
-
OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis
OrganicHAR discovers 4-8 activity categories per user from sensor signals, achieves 79% accuracy on coarse activities with ambient sensors alone and cuts VLM queries by 90% by triggering video analysis only at detected pattern moments.
-
LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition
LastAct creates layout-aligned trajectory images from sensor events and applies boundary-guided masking to improve Macro-F1 on mixed sliding windows in smart-home HAR.