no code implementations • 10 Dec 2023 • Wenju Xu, Chengjiang Long, Yongwei Nie, Guanghui Wang
Unlike the existing works leveraging the semantic masks to obtain the representation of each component, we propose to generate disentangled latent code via a novel attribute encoder with transformers trained in a manner of curriculum learning from a relatively easy step to a gradually hard one.
no code implementations • CVPR 2023 • Zhijun Zhai, Jianhui Zhao, Chengjiang Long, Wenju Xu, Shuangjiang He, Huijuan Zhao
Micro-expressions are spontaneous, rapid and subtle facial movements that can neither be forged nor suppressed.
Micro Expression Recognition Micro-Expression Recognition +2
no code implementations • CVPR 2023 • Wenju Xu, Chengjiang Long, Yongwei Nie
Arbitrary style transfer has been demonstrated to be efficient in artistic image generation.
1 code implementation • 25 Oct 2022 • Xiangyu Chen, Ying Qin, Wenju Xu, Andrés M. Bur, Cuncong Zhong, Guanghui Wang
To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain.
no code implementations • 22 Jan 2022 • Ying Wang, Chiuman Ho, Wenju Xu, Ziwei Xuan, Xudong Liu, Guo-Jun Qi
We propose a Dual-Flattening Transformer (DFlatFormer) to enable high-resolution output by reducing complexity to $\mathcal{O}(hw(H+W))$ that is multiple orders of magnitude smaller than the naive dense transformer.
no code implementations • 21 Oct 2021 • Wenju Xu, Guanghui Wang
Existing approaches rely on a cycle-consistency constraint that supervises the generators to learn an inverse mapping.
Generative Adversarial Network Image-to-Image Translation +1
1 code implementation • ICCV 2021 • Wenju Xu, Chengjiang Long, Ruisheng Wang, Guanghui Wang
The style code is modeled as the shared parameters for Dynamic ResBlocks connecting both the style encoding network and the style transfer network.
1 code implementation • 5 Aug 2021 • Xinzhi Dong, Chengjiang Long, Wenju Xu, Chunxia Xiao
With the well-designed Dual-GCN, we can make the linguistic transformer better understand the relationship between different objects in a single image and make full use of similar images as auxiliary information to generate a reasonable caption description for a single image.
no code implementations • 4 Oct 2019 • Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang
In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations.
no code implementations • 4 Oct 2019 • Wenju Xu, Dongkyu Choi, Guanghui Wang
The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking.
no code implementations • arXiv 2019 • Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang
In this paper, we address the problem of weakly supervisedobject localization (WSL), which trains a detection network on the datasetwith only image-level annotations.
no code implementations • 4 Oct 2019 • Wenju Xu, Shawn Keshmiri, Guanghui Wang
At the first stage, the SWAE flexibly learns a representation distribution, i. e., the encoded prior; and at the second stage, the encoded representation distribution is approximated with a latent variable model under the regularization encouraging the latent distribution to match the explicit prior.
no code implementations • 21 May 2019 • Wenju Xu, Shawn Keshmiri, Guanghui Wang
Image-to-image translation, which translates input images to a different domain with a learned one-to-one mapping, has achieved impressive success in recent years.
no code implementations • 2 Mar 2019 • Ziming Zhang, Wenju Xu, Alan Sullivan
In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization.
no code implementations • 14 Feb 2019 • Wenju Xu, Shawn Keshmiri, Guanghui Wang
Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes.