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.
Sigmoid- weighted linear units for neural network function approxima- tion in reinforcement learning.Neural networks, 107:3–11,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.
MambaLiteUNet integrates Mamba into U-Net with adaptive fusion, local-global mixing, and cross-gated attention modules to reach 87.12% IoU and 93.09% Dice on skin lesion datasets while cutting parameters by 93.6%.
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.
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.
-
MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
MambaLiteUNet integrates Mamba into U-Net with adaptive fusion, local-global mixing, and cross-gated attention modules to reach 87.12% IoU and 93.09% Dice on skin lesion datasets while cutting parameters by 93.6%.