no code implementations • 6 Jun 2023 • Minting Pan, Yitao Zheng, Wendong Zhang, Yunbo Wang, Xiaokang Yang
Pretraining RL models on offline video datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in tasks, dynamics, and behaviors across domains.
no code implementations • 19 Apr 2023 • Wendong Zhang
Recent research in this field has primarily centered around multimodal approaches for addressing this issue. In this paper, a multimodal fusion approach based on result feature-level fusion is proposed.
no code implementations • 16 Apr 2023 • Wendong Zhang, Qingjie Chai, Quanqi Zhang, ChengWei Wu
Therefore, this paper proposes an Obstacle-Transformer to predict trajectory in a constant inference time.
no code implementations • 12 Mar 2023 • Haijian Chen, Wendong Zhang, Yunbo Wang, Xiaokang Yang
Masked image modeling is a promising self-supervised learning method for visual data.
2 code implementations • 12 Mar 2023 • Wendong Zhang, Geng Chen, Xiangming Zhu, Siyu Gao, Yunbo Wang, Xiaokang Yang
In this paper, we present a new continual learning approach for visual dynamics modeling and explore its efficacy in visual control and forecasting.
1 code implementation • 21 Sep 2022 • Xiangzuo Huo, Gang Sun, Shengwei Tian, Yan Wang, Long Yu, Jun Long, Wendong Zhang, Aolun Li
A parallel hierarchy of local and global feature blocks is designed to efficiently extract local features and global representations at various semantic scales, with the flexibility to model at different scales and linear computational complexity relevant to image size.
1 code implementation • CVPR 2022 • Geng Chen, Wendong Zhang, Han Lu, Siyu Gao, Yunbo Wang, Mingsheng Long, Xiaokang Yang
Can we develop predictive learning algorithms that can deal with more realistic, non-stationary physical environments?
1 code implementation • 8 Dec 2021 • Wendong Zhang, Yunbo Wang, Bingbing Ni, Xiaokang Yang
We train the prior learner and the image generator as a unified model without any post-processing.
1 code implementation • 14 Jun 2021 • Wendong Zhang, Junwei Zhu, Ying Tai, Yunbo Wang, Wenqing Chu, Bingbing Ni, Chengjie Wang, Xiaokang Yang
Based on the semantic priors, we further propose a context-aware image inpainting model, which adaptively integrates global semantics and local features in a unified image generator.
no code implementations • CVPR 2019 • Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang
Person re-identification has achieved great progress with deep convolutional neural networks.
no code implementations • 1 Jun 2017 • Wendong Zhang, Bingbing Ni, Yichao Yan, Jingwei Xu, Xiaokang Yang
Key to automatically generate natural scene images is to properly arrange among various spatial elements, especially in the depth direction.