27 citations · 41 across the 9 of their papers we have counts for
9 papers
Latent Dynamics for Full Body Avatar Animation
Shichong Peng, Chengxiang Yin, Fei Jiang +7
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 al…
FactorPortrait: Controllable Portrait Animation via Disentangled Expression, Pose, and Viewpoint
Jiapeng Tang, Kai Li, Chengxiang Yin +8
We introduce FactorPortrait, a video diffusion method for controllable portrait animation that enables lifelike synthesis from disentangled control signals of facial expressions, h…
FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images
Rong Wang, Fabian Prada, Ziyan Wang +10
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 c…
ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
Kun Wu, Yinuo Zhao, Zhiyuan Xu +5
Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a saf…
Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering
Chengxiang Yin, Zhengping Che, Kun Wu +2
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 in…
Cross-Modal Reasoning with Event Correlation for Video Question Answering
Chengxiang Yin, Zhengping Che, Kun Wu +3
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…
Continual Few-Shot Learning with Adversarial Class Storage
Kun Wu, Chengxiang Yin, Jian Tang +3
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 suc…
Human Pose Transfer with Augmented Disentangled Feature Consistency
Kun Wu, Chengxiang Yin, Zhengping Che +4
Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have…
Adversarial Meta-Learning
Chengxiang Yin, Jian Tang, Zhiyuan Xu +1
Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta…