Yang Wu

Yang Wu

Auto-generated profile, based on publicly available information

Yang Wu

Tencent AI Lab, Shenzhen, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 December 2020
Verified
Book Chapter
Closed access
PDF file
ZZZiqiang Zheng
Ziqiang Zheng
YWYang Wu
Yang Wu
XHXinran Han
Xinran Han
JSJianbo Shi
Jianbo Shi

23 July 2023
Verified
Conference Paper
Open access
WYWangbo Yu
Wangbo Yu
YFYanbo Fan
Yanbo Fan
YZYong Zhang
Yong Zhang
XWXuan Wang
Xuan Wang
FYFei Yin
Fei Yin
BWBaoyuan Wu
Baoyuan Wu
3D facial avatar reconstruction has been a significant research topic in computer graphics and computer vision, where photo-realistic rendering and flexible controls over poses and expressions are necessary for many related applications. Recently, its performance has been greatly improved with the development of neural radiance fields (NeRF). However, most existing NeRF-based facial avatars focus on subject-specific reconstruction and reenactment, requiring multi-shot images containing different views of the specific subject for training, and the learned model cannot generalize to new identities, limiting its further applications. In this work, we propose a one-shot 3D facial avatar reconstruction framework that only requires a single source image to reconstruct a high-fidelity 3D facial avatar. For the challenges of lacking generalization ability and missing multi-view information, we leverage the generative prior of 3D GAN and develop an efficient encoder-decoder network to reconstruct the canonical neural volume of the source image, and further propose a compensation network to complement facial details. To enable fine-grained control over facial dynamics, we propose a deformation field to warp the canonical volume into driven expressions. Through extensive experimental comparisons, we achieve superior synthesis results compared to several state-of-the-art methods.

15 January 2024 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
XGXuehao Gao
Xuehao Gao
Yang YangYang Yang
Yang Yang
ZXZhenyu Xie
Zhenyu Xie
SDShaoyi Du
Shaoyi Du
ZSZhongqian Sun
Zhongqian Sun
YWYang Wu
Yang Wu
In this paper, we propose a novel cascaded diffusion-based generative framework for text-driven human motion synthesis, which exploits a strategy named G rad U ally E nriching S ynthe S is ( GUESS as its abbreviation). The strategy sets up generation objectives by grouping body joints of detailed skeletons in close semantic proximity together and then replacing each of such joint group with a single body-part node. Such an operation recursively abstracts a human pose to coarser and coarser skeletons at multiple granularity levels. Notably, we further integrate GUESS with the proposed dynamic multi-condition fusion mechanism to dynamically balance the cooperative effects of the given textual condition and synthesized coarse motion prompt in different generation stages. Extensive experiments on large-scale datasets verify that GUESS outperforms existing state-of-the-art methods by large margins in terms of accuracy, realisticness, and diversity. Please refer to the supplemental demo video for more visualizations.

27 March 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XGXuehao Gao
Xuehao Gao
Yang YangYang Yang
Yang Yang
YWYang Wu
Yang Wu
SDShaoyi Du
Shaoyi Du
Graph convolution networks (GCNs) have been widely used and achieved fruitful progress in the skeleton-based action recognition task. In GCNs, node interaction modeling dominates the context aggregation and, therefore, is crucial for a graph-based convolution kernel to extract representative features. In this article, we introduce a closer look at a powerful graph convolution formulation to capture rich movement patterns from these skeleton-based graphs. Specifically, we propose a novel heterogeneous graph convolution (HetGCN) that can be considered as the middle ground between the extremes of (2 $+$ 1)-D and 3-D graph convolution. The core observation of HetGCN is that multiple information flows are jointly intertwined in a 3-D convolution kernel, including spatial, temporal, and spatial–temporal cues. Since spatial and temporal information flows characterize different cues for action recognition, HetGCN first dynamically analyzes pairwise interactions between each node and its cross-space–time neighbors and then encourages heterogeneous context aggregation among them. Considering the HetGCN as a generic convolution formulation, we further develop it into two specific instantiations (i.e., intra-scale and inter-scale HetGCN) that significantly facilitate cross-space–time and cross-scale learning on skeleton graphs. By integrating these modules, we propose a strong human action recognition system that outperforms state-of-the-art methods with the accuracy of 93.1% on NTU-60 cross-subject (X-Sub) benchmark, 88.9% on NTU-120 X-Sub benchmark, and 38.4% on kinetics skeleton.

14 November 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
CLCe Li
Ce Li
FLFenghua Liu
Fenghua Liu
ZTZhiqiang Tian
Zhiqiang Tian
SDShaoyi Du
Shaoyi Du
YWYang Wu
Yang Wu
Deep-learning-based salient object detection (SOD) has achieved significant success in recent years. The SOD focuses on the context modeling of the scene information, and how to effectively model the context relationship in the scene is the key. However, it is difficult to build an effective context structure and model it. In this article, we propose a novel SOD method called dynamic and adaptive graph convolutional network (DAGCN) that is composed of two parts, adaptive neighborhood-wise graph convolutional network (AnwGCN) and spatially restricted K-nearest neighbors (SRKNN). The AnwGCN is novel adaptive neighborhood-wise graph convolution, which is used to model and analyze the saliency context. The SRKNN constructs the topological relationship of the saliency context by measuring the non-Euclidean spatial distance within a limited range. The proposed method constructs the context relationship as a topological graph by measuring the distance of the features in the non-Euclidean space, and conducts comparative modeling of context information through AnwGCN. The model has the ability to learn the metrics from features and can adapt to the hidden space distribution of the data. The description of the feature relationship is more accurate. Through the convolutional kernel adapted to the neighborhood, the model obtains the structure learning ability. Therefore, the graph convolution process can adapt to different graph data. Experimental results demonstrate that our solution achieves satisfactory performance on six widely used datasets and can also effectively detect camouflaged objects. Our code will be available at: https://github.com/ CSIM-LUT/DAGCN.git.

24 February 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HRHao Ren
Hao Ren
ZZZiqiang Zheng
Ziqiang Zheng
YWYang Wu
Yang Wu
HLHong Lu
Hong Lu
YYYang Yang
Yang Yang
SYSai-Kit Yeung
Sai-Kit Yeung
The huge domain gap between sketches and photos poses huge challenges for Sketch-Based Image Retrieval (SBIR). The Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is more generic and practical but brings an even greater challenge: the additional knowledge gap between the seen and unseen categories. In order to simultaneously mitigate both gaps, we propose an Approaching-and-Centralizing Network (termed “ACNet”) to jointly optimize sketch-to-photo synthesis and image retrieval. The retrieval module guides the synthesis module to generate large amounts of diverse photo-like images that help the sketch domain gradually approach the photo domain to eliminate the domain gap, and thus better serves retrieval. Meanwhile, the retrieval module itself centralizes the embeddings of training samples for learning a similarity measurement to eliminate the knowledge gap. Our approach is simple yet effective, which achieves state-of-the-art performance on two widely used ZS-SBIR datasets and surpasses previous methods by a large margin ( e.g ., 8.2% improvement in terms of mAP@all on TU-Berlin Extended dataset).