Article

Skeleton Motion Super-Resolution via Masked CP Decomposition in Latent Embedding Space

2026-06-11

Abstract excerpt

<title>Abstract</title> <p>We propose a latent-space approach for temporal super-resolution of human skeleton motion using masked CANDECOMP/PARAFAC (CP) tensor decomposition. Building on our previous work, which established a smooth and continuous embedding space through a regularized autoencoder, this study extends the framework to explicitly model intrinsic temporal components within the latent representation....

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 435dfe80-35b6-5a86-af72-0fedd2951bd1
DOI: 10.21203/rs.3.rs-8146232/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Skeleton Motion Super-Resolution via Masked CP Decomposition in Latent Embedding SpaceDOI 10.21203/rs.3.rs-8146232/v1Read

A Spatiotemporal Bidirectional Mamba Network with Global–Local Skeletal Enhancement for 3D Human Pose EstimationSemantic proximity Read

SimpleCID: Skeleton-Guided Lightweight Heatmap Refinement for Robust Multi-Person Pose Estimation in Crowded ScenesSemantic proximity Read

SRHPENet: Super-Resolution Network for human pose estimationSemantic proximity Read

A Latent Space Diffusion Transformer for High-Quality Video Frame InterpolationSemantic proximity Read

Human Behavior Recognition Based on Graph Neural Network and Cross-modal Collaborative Attention MechanismSemantic proximity Read

A Two-Stream Deep Learning Approach for Enhanced Two-Person Human Interaction Recognition in VideosSemantic proximity Read

Towards Human-Centered and Efficient Video Synthesis: A Survey of Multimodal Diffusion ModelsSemantic proximity Read

Monocular 3D Human Pose-Estimation Networks for Coherent Humanoid-Model DrivingSemantic proximity Read

A Real-Time Motion Deblurring Network for Sports- Related Dynamic Scenes Based on Lightweight GANSemantic proximity Read

TransMODAL: A Dual-Stream Transformer with Adaptive Co-Attention for Efficient Human Action RecognitionSemantic proximity Read

MSTPose: Learning Enriched Visual Information with Multi-Scale Transformers for Human Pose EstimationSemantic proximity Read

Adaptive Graph Convolution Embedding Normalizing Flow for Video Anomaly DetectionSemantic proximity Read