Searcharxiv⌕ Search

arXiv subjects

Guangming Wu

Publications and source records attributed to Guangming Wu.

5 recordsLinked to original sources
arXiv2026

SeMoCo: A Semantic-First Motion Codec for Motion Language Modeling

Discrete motion representations have substantially advanced autoregressive text-to-motion generation. However, most motion tokenizers are optimized for reconstruction and do not explicitly allocate capacity according to semantic role. Action-level meaning and fine-grained kinematic detail must therefore be encoded through the same reconstruction-driven hierarchy. We introduce SeMoCo, a semantic-first motion codec, together with a dual-axis motion generator for language-conditioned motion generation. Each motion token contains one semantic token and a residual sequence of kinematic tokens. The generator models semantic progression across time and autoregressively refines the residual entries. We also construct $\Omega$-MotionVerse, a large-scale, multi-source human-motion dataset unified under the SOMA representation. Across the reported comparisons, SeMoCo achieves the best reconstruction accuracy among the compared codecs, while strong text-to-motion results demonstrate the effectiveness of its motion tokens for downstream generation.

cs.CV↗
arXiv2020

Ultra-slow sound in non-resonant meta-aerogel

The manipulation of sound with acoustic metamaterials is a field of intense research, where interaction via resonance is a common application despite the significant disadvantages. We propose a novel procedure for introducing well-designed coupling interfaces with a cell size of less than 10 nm into an ultra-soft porous medium, to prepare a meta-aerogel, where the sound propagation is significantly delayed in a non-resonant mode. The resultant sound velocity is shown as a scaling law with the mass density and the mass fraction ratio of the components, in accordance with our analytical model. We have prepared a meta-aerogel with the slowest sound velocity of 62 m/s. To the best of our knowledge, this is the lowest value in compact solid materials, with a prospect of further slowing down by our procedure. The development of such meta-aerogels can facilitate key applications in acoustic metamaterials intended to employ non-resonant type slow sound (or phase delay). Examples of the latter include deep subwavelength meta-surface and other focused imaging or transformation acoustics that require a high contrast of sound velocity.

physics.app-ph↗
arXiv2018

Semantic Segmentation for Urban Planning Maps based on U-Net

The automatic digitizing of paper maps is a significant and challenging task for both academia and industry. As an important procedure of map digitizing, the semantic segmentation section mainly relies on manual visual interpretation with low efficiency. In this study, we select urban planning maps as a representative sample and investigate the feasibility of utilizing U-shape fully convolutional based architecture to perform end-to-end map semantic segmentation. The experimental results obtained from the test area in Shibuya district, Tokyo, demonstrate that our proposed method could achieve a very high Jaccard similarity coefficient of 93.63% and an overall accuracy of 99.36%. For implementation on GPGPU and cuDNN, the required processing time for the whole Shibuya district can be less than three minutes. The results indicate the proposed method can serve as a viable tool for urban planning map semantic segmentation task with high accuracy and efficiency.

cs.LG↗
arXiv2018

Geoseg: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction

Recently, deep learning algorithms, especially fully convolutional network based methods, are becoming very popular in the field of remote sensing. However, these methods are implemented and evaluated through various datasets and deep learning frameworks. There has not been a package that covers these methods in a unifying manner. In this study, we introduce a computer vision package termed Geoseg that focus on building segmentation and outline extraction. Geoseg implements over nine state-of-the-art models as well as utility scripts needed to conduct model training, logging, evaluating and visualization. The implementation of Geoseg emphasizes unification, simplicity, and flexibility. The performance and computational efficiency of all implemented methods are evaluated by comparison experiment through a unified, high-quality aerial image dataset.

cs.CV↗