FaceMamba: Geometry‐Aware Mamba for Efficient Speech‐Driven 3D Facial Animation
Abstract Speech‐driven 3D facial animation plays a pivotal role in immersive digital human applications. Recent works have explored Mamba‐based sequence modeling as an efficient alternative to Transformer, but they often suffer from limited cross‐modal alignment and insufficient control over fine‐grained facial deformations.
Yifan Ge +5 more
wiley +1 more source
Reassessment of two finite-element studies of infant head trauma: limits of the modelling evidence for shaking-induced bridging-vein rupture and protection by enlarged subarachnoid spaces. [PDF]
Rossant C, Button KD.
europepmc +1 more source
A Splitting Architecture for Exact Reduced Coulomb Friction
Abstract Existing approaches to frictional contact dynamics typically either modify the Coulomb law to improve numerical robustness or solve the exact law in a fully coupled monolithic form. However, in its reduced form, exact Coulomb friction can be written as a cone complementarity problem with an augmented velocity, which reveals a natural split ...
Hongcheng Song +3 more
wiley +1 more source
Impact of the Lower Body on Softball Pitching Velocity. [PDF]
Jump IP +5 more
europepmc +1 more source
Advances in 4D Representation: Geometry, Motion, and Interaction
We survey 4D representation through three key pillars — geometry, motion, and interaction — offering a selective, representation‐centric perspective to guide researchers in choosing and customizing the right 4D representation for their tasks. Abstract We present a survey on 4D generation and reconstruction, a fast‐evolving subfield of computer graphics
M. Zhao +7 more
wiley +1 more source
Stance-phase kinematic descriptors differentiate clinical subgroups in women with moderate knee osteoarthritis. [PDF]
Loayza-Saldaña MA +6 more
europepmc +1 more source
Dancing Points: Synthesizing Ballroom Dancing With Three‐Point Inputs
From a dancer's head and hands motion captured by VR devices, we synthesize full‐body ballroom dancing for both leader and follower dancers. We decompose this dual‐character synthesis into jointly predicting both dancers' three‐point trajectories, then recovering each full body independently, resulting in a stable, responsive model trained with limited
Peizhuo Li +3 more
wiley +1 more source
Dynamic Occlusion-Predictive Neural Network for Robust Roadside Multi-Vehicle Tracking. [PDF]
Wang S, Wang Y, Wang B, Wei C, Liu H.
europepmc +1 more source
Machine learning approaches in automated infant General Movements Assessment: A scoping review
Automated infant General Movements Assessment increasingly uses machine‐ and deep‐learning approaches to classify movement patterns and estimate cerebral palsy risk from video or sensor data. This scoping review highlights how dataset characteristics, recording environment, pose‐estimation accuracy, feature extraction, and model design influence system
Manpreet Kaur +4 more
wiley +1 more source
Quantification of daily upper arm use after stroke using an IMU-based kinematic model. [PDF]
Goldhamer N +5 more
europepmc +1 more source

