Search Results for author: Congyi Wang

Found 7 papers, 0 papers with code

T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations

no code implementations17 Dec 2023 Congyi Wang

This vector then serves as a context prompt for the residual GPT, which generates the final residual discrete indices.

HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation

no code implementations29 Jul 2023 Zuyan Liu, Gaojie Lin, Congyi Wang, Min Zheng, Feida Zhu

Our approach involves a unified and multi-granularity strategy that includes a pseudo keypoint alignment module in the teacher-student framework for learning pose-aware semantic class tokens.

Pose Estimation regression +2

MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction

no code implementations CVPR 2023 Congyi Wang, Feida Zhu, Shilei Wen

Existing methods proposed for hand reconstruction tasks usually parameterize a generic 3D hand model or predict hand mesh positions directly.

Vocal Bursts Valence Prediction

Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images

no code implementations22 Jun 2021 Liguo Jiang, Miaopeng Li, Jianjie Zhang, Congyi Wang, Juntao Ye, Xinguo Liu, Jinxiang Chai

We show the system advances the frontier of 3D human body and pose reconstruction from single images by quantitative evaluations and comparisons with state-of-the-art methods.

Foreground Segmentation

Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN

no code implementations26 Mar 2021 Congyi Wang, Yu Chen, Bin Wang, Yi Shi

GAN-based neural vocoders, such as Parallel WaveGAN and MelGAN have attracted great interest due to their lightweight and parallel structures, enabling them to generate high fidelity waveform in a real-time manner.

Polyphone Disambiguition in Mandarin Chinese with Semi-Supervised Learning

no code implementations1 Feb 2021 Yi Shi, Congyi Wang, Yu Chen, Bin Wang

In this paper, we propose a novel semi-supervised learning (SSL) framework for Mandarin Chinese polyphone disambiguation that can potentially leverage unlimited unlabeled text data.

Polyphone disambiguation

Music2Dance: DanceNet for Music-driven Dance Generation

no code implementations2 Feb 2020 Wenlin Zhuang, Congyi Wang, Siyu Xia, Jinxiang Chai, Yangang Wang

Synthesize human motions from music, i. e., music to dance, is appealing and attracts lots of research interests in recent years.

Motion Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.