E-3DPSM introduces an event-driven continuous pose state machine that aligns human motion with event dynamics, fuses latent state updates with direct predictions, and achieves up to 19% better MPJPE accuracy plus 2.7x temporal stability on benchmarks.
How to train your differentiable filter.Autonomous Robots, 45(4): 561–578, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimation
E-3DPSM introduces an event-driven continuous pose state machine that aligns human motion with event dynamics, fuses latent state updates with direct predictions, and achieves up to 19% better MPJPE accuracy plus 2.7x temporal stability on benchmarks.