Jingwei Xu

Jingwei Xu

Auto-generated profile, based on publicly available information

Jingwei Xu

Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
27 July 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SGShanyan Guan
Shanyan Guan
JXJingwei Xu
Jingwei Xu
MHMichelle Zhang He
Michelle Zhang He
YWYunbo Wang
Yunbo Wang
BNBingbing Ni
Bingbing Ni
XYXiaokang Yang
Xiaokang Yang
We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where the performance of existing SMPL-based models is significantly affected by the distribution shift represented by different camera parameters, bone lengths, backgrounds, and occlusions. We tackle this problem through online adaptation, gradually correcting the model bias during testing. There are two main challenges: First, the lack of 3D annotations increases the training difficulty and results in 3D ambiguities. Second, non-stationary data distribution makes it difficult to strike a balance between fitting regular frames and hard samples with severe occlusions or dramatic changes. To this end, we propose the Dynamic Bilevel Online Adaptation algorithm (DynaBOA). It first introduces the temporal constraints to compensate for the unavailable 3D annotations and leverages a bilevel optimization procedure to address the conflicts between multi-objectives. DynaBOA provides additional 3D guidance by co-training with similar source examples retrieved efficiently despite the distribution shift. Furthermore, it can adaptively adjust the number of optimization steps on individual frames to fully fit hard samples and avoid overfitting regular frames. DynaBOA achieves state-of-the-art results on three out-of-domain human mesh reconstruction benchmarks.

6 December 2018 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
Yichao YanYichao Yan
Yichao Yan
BNBingbing Ni
Bingbing Ni
WZWendong Zhang
Wendong Zhang
JXJingwei Xu
Jingwei Xu
XYXiaokang Yang
Xiaokang Yang
Video generation is a challenging task due to the extreme high-dimensional distribution of the solution space. Good constraints in the solution domain would thus reduce the difficulty of approximating optimal solutions. In this work, instead of directly generating high-dimensional video data, we propose using object landmarks as explicit structure constraints to address this issue. Specifically, we propose a two-stage framework for an action-conditioned video generation task. In our framework, the first stage aims to generate landmark sequences according to predefined motion types, and a recurrent model (RNN/LSTM) is adopted for this purpose. The landmark sequence can be regarded as a low-dimensional structure embedding of high-dimensional video data, and generating landmark sequences is much easier compared to generating videos. The second stage is inspired by a conditional generative adversarial network (CGAN), and we take the generated landmark sequence as structure condition to learn a landmark-to-image translation network. Such a one-to-one translation framework avoids the difficulty of generating videos and instead transfers the video generation task to image generation, which is resolvable due to the maturity of current GAN-based models. The experimental results demonstrate that our model not only achieves promising results on rigid/non-rigid motion generation tasks but can also be extended to multi-object motion situations.

22 October 2020 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
JXJingwei Xu
Jingwei Xu
BNBingbing Ni
Bingbing Ni
XYXiaokang Yang
Xiaokang Yang

15 October 2018
Verified
Conference Paper
Open access
WZWendong Zhang
Wendong Zhang
Feng GaoFeng Gao
Feng Gao
BNBingbing Ni
Bingbing Ni
LDLingyu Duan
Lingyu Duan
Yichao YanYichao Yan
Yichao Yan
XYXiaokang Yang
Xiaokang Yang