Chengxiang Yin

Latent Dynamics for Full Body Avatar Animation

Shichong Peng, Chengxiang Yin, Fei Jiang, Zhongshi Jiang et autres

Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements deform in ways pose alone cannot explain: the same pose can correspond to many different states, because their motion depends …

Latent Dynamics for Full Body Avatar Animation

Shichong Peng, Chengxiang Yin, Fei Jiang, Zhongshi Jiang et autres

Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements deform in ways pose alone cannot explain: the same pose can correspond to many different states, because their motion depends …

FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

Rong Wang, Fabián Prada, Ziyan Wang, Zhongshi Jiang et autres

We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images. Due to the large variations in body shapes, poses, and cloth types, existing methods mostly require hours of per-subject optimization during inference, which …

au, us (code pays fourni par la source)

ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning

Kun Wu, Yinuo Zhao, Zhiyuan Xu, Zhengping Che et autres

Offline reinforcement learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods typically learn a conservative policy to mitigate the problem of Q-value …

cn, us (code pays fourni par la source)

Cross-Modal Reasoning with Event Correlation for Video Question Answering

Chengxiang Yin, Zhengping Che, Kun Wu, Zhiyuan Xu et autres

Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i.e., the spatio-temporal video content and the word sequence in question. Although various attention mechanisms have been utilized to …

Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering

Chengxiang Yin, Zhengping Che, Kun Wu, Zhiyuan Xu et autres

Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature. However, most existing VQA methods are incapable of handling Knowledge-based Visual Question Answering (KB-VQA), which requires external knowledge beyond visible contents …

Simulation Study on Real-Time Orbit Determination Based on GNSS for LEO Satellite Considering the Effect of Electric Propulsion

Jiapeng Wu, Wanwei Zhang, Fuhong Wang, Meng Wang et autres

cn (code pays fourni par la source)

Human Pose Transfer with Augmented Disentangled Feature Consistency

Kun Wu, Chengxiang Yin, Zhengping Che, Bo Jiang et autres

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring the poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity, the main challenge remains and …

us, cn (code pays fourni par la source)

Direct Acquisition Method of Segmented Configurable BDS P-code Signal Based on FFT Parallel One-dimensional Search

Qi Ren, Chengxiang Yin, Yu Xia Qian, Yan Peng et autres

BDS P-code signals direct acquisition is a must-have capability for missile weapons products guided by BeiDou Navigation Satellite System in electronic warfare and navigation warfare environments. The direct acquisition method of segmented configurable BDS P-code signal based on FFT parallel one-dimensional search …

Continual Few-Shot Learning with Adversarial Class Storage

Kun Wu, Chengxiang Yin, Jian Tang, Zhiyuan Xu et autres

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges for achieving such human-level intelligence. In this …

Sequence-to-Sequence Learning for Prediction of Soil Temperature and Moisture

Xiaojie Li, Jian Tang, Chengxiang Yin

Soil temperature and moisture play a significant influence on vegetation and climate. Measurements of soil temperature and moisture can now be obtained through soil temperature and moisture sensors, but the measurements can only be done for a specified period of time in …

cn, us (code pays fourni par la source)

Understanding the mineralogy and geochemistry of Chang'E-5 soil and implications for its geological significances

Xiaohui Fu, Chengxiang Yin, Bradley L. Jolliff, Jiang Zhang et autres

Here we present the mineralogical and chemical data sources of Apollo, Luna, and Chang'E-5 (CE-5) missions. All the data are complied from previous studies. More reference details can be found in each excel files. Table S1 Modal mineralogy of Apollo and CE-5 …