Search Results for author: Yuwang Wang

Found 21 papers, 6 papers with code

Context-aware Talking Face Video Generation

no code implementations28 Feb 2024 Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Qionghai Dai

To achieve this, we provide a two-stage and cross-modal controllable video generation pipeline, taking facial landmarks as an explicit and compact control signal to bridge the driving audio, talking context and generated videos.

Video Generation Video Synchronization

DisControlFace: Disentangled Control for Personalized Facial Image Editing

no code implementations11 Dec 2023 Haozhe Jia, Yan Li, Hengfei Cui, Di Xu, Changpeng Yang, Yuwang Wang, Tao Yu

Our DisControlNet can perform robust editing on any facial image through training on large-scale 2D in-the-wild portraits and also supports low-cost fine-tuning with few additional images to further learn diverse personalized priors of a specific person.

Breaking through the learning plateaus of in-context learning in Transformer

no code implementations12 Sep 2023 Jingwen Fu, Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng

To study the mechanism behind the learning plateaus, we conceptually seperate a component within the model's internal representation that is exclusively affected by the model's weights.

In-Context Learning Representation Learning

Shape Guided Gradient Voting for Domain Generalization

no code implementations19 Jun 2023 Jiaqi Xu, Yuwang Wang, Xuejin Chen

In this work, with the assumption that the gradients of a specific domain samples under the classification task could also reflect the property of the domain, we propose a Shape Guided Gradient Voting (SGGV) method for domain generalization.

Domain Generalization Image Classification

Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization

no code implementations29 May 2023 Tao Yang, Yuwang Wang, Cuiling Lan, Yan Lu, Nanning Zheng

In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization.

Disentanglement

Super-NeRF: View-consistent Detail Generation for NeRF super-resolution

no code implementations26 Apr 2023 Yuqi Han, Tao Yu, Xiaohang Yu, Yuwang Wang, Qionghai Dai

Given multi-view low-resolution images, Super-NeRF constructs a consistency-controlling super-resolution module to generate view-consistent high-resolution details for NeRF.

Image Super-Resolution

Hi Sheldon! Creating Deep Personalized Characters from TV Shows

no code implementations9 Apr 2023 Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Xiao Ma, Yuchen Guo, Tao Yu, Qionghai Dai

To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows.

Unifying Layout Generation with a Decoupled Diffusion Model

no code implementations CVPR 2023 Mude Hui, Zhizheng Zhang, Xiaoyi Zhang, Wenxuan Xie, Yuwang Wang, Yan Lu

Since different attributes have their individual semantics and characteristics, we propose to decouple the diffusion processes for them to improve the diversity of training samples and learn the reverse process jointly to exploit global-scope contexts for facilitating generation.

Template-guided Hierarchical Feature Restoration for Anomaly Detection

no code implementations ICCV 2023 Hewei Guo, Liping Ren, Jingjing Fu, Yuwang Wang, Zhizheng Zhang, Cuiling Lan, Haoqian Wang, Xinwen Hou

Targeting for detecting anomalies of various sizes for complicated normal patterns, we propose a Template-guided Hierarchical Feature Restoration method, which introduces two key techniques, bottleneck compression and template-guided compensation, for anomaly-free feature restoration.

Anomaly Detection

Visual Concepts Tokenization

2 code implementations20 May 2022 Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng

We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts.

Representation Learning

Test-time Batch Normalization

no code implementations20 May 2022 Tao Yang, Shenglong Zhou, Yuwang Wang, Yan Lu, Nanning Zheng

Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift.

Domain Generalization

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

2 code implementations ICLR 2022 Dacheng Yin, Xuanchi Ren, Chong Luo, Yuwang Wang, Zhiwei Xiong, Wenjun Zeng

Last, an innovative link attention module serves as the decoder to reconstruct data from the decomposed content and style, with the help of the linking keys.

Quantization Style Transfer +1

Understanding Mobile GUI: from Pixel-Words to Screen-Sentences

no code implementations25 May 2021 Jingwen Fu, Xiaoyi Zhang, Yuwang Wang, Wenjun Zeng, Sam Yang, Grayson Hilliard

A dataset, RICO-PW, of screenshots with Pixel-Words annotations is built based on the public RICO dataset, which will be released to help to address the lack of high-quality training data in this area.

Retrieval Sentence

S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation

4 code implementations CVPR 2021 Xiaotian Chen, Yuwang Wang, Xuejin Chen, Wenjun Zeng

S2R-DepthNet consists of: a) a Structure Extraction (STE) module which extracts a domaininvariant structural representation from an image by disentangling the image into domain-invariant structure and domain-specific style components, b) a Depth-specific Attention (DSA) module, which learns task-specific knowledge to suppress depth-irrelevant structures for better depth estimation and generalization, and c) a depth prediction module (DP) to predict depth from the depth-specific representation.

Depth Prediction Domain Generalization +2

Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View

2 code implementations ICLR 2022 Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng

Based on this observation, we argue that it is possible to mitigate the trade-off by $(i)$ leveraging the pretrained generative models with high generation quality, $(ii)$ focusing on discovering the traversal directions as factors for disentangled representation learning.

Contrastive Learning Disentanglement

Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement

1 code implementation21 Feb 2021 Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng

From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias.

3D Reconstruction Disentanglement +4

Towards Building A Group-based Unsupervised Representation Disentanglement Framework

1 code implementation ICLR 2022 Tao Yang, Xuanchi Ren, Yuwang Wang, Wenjun Zeng, Nanning Zheng

We then propose a model, based on existing VAE-based methods, to tackle the unsupervised learning problem of the framework.

Disentanglement

Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks

no code implementations13 Apr 2020 Wei Zhou, Qiuping Jiang, Yuwang Wang, Zhibo Chen, Weiping Li

Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions.

Image Quality Assessment

Unsupervised High-Resolution Depth Learning From Videos With Dual Networks

no code implementations ICCV 2019 Junsheng Zhou, Yuwang Wang, Kaihuai Qin, Wen-Jun Zeng

Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal.

Monocular Depth Estimation Vocal Bursts Intensity Prediction

Adversarial View-Consistent Learning for Monocular Depth Estimation

no code implementations4 Aug 2019 Yixuan Liu, Yuwang Wang, Shengjin Wang

To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner.

Monocular Depth Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.