Search Results for author: Can Wang

Found 59 papers, 35 papers with code

Motif-driven Subgraph Structure Learning for Graph Classification

1 code implementation13 Jun 2024 Zhiyao Zhou, Sheng Zhou, Bochao Mao, Jiawei Chen, Qingyun Sun, Yan Feng, Chun Chen, Can Wang

Notably, applying node-level GSL to graph classification is non-trivial due to the lack of find-grained guidance for intricate structure learning.

Graph Classification Graph structure learning

On the Trajectory Regularity of ODE-based Diffusion Sampling

2 code implementations18 May 2024 Defang Chen, Zhenyu Zhou, Can Wang, Chunhua Shen, Siwei Lyu

Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution.

Denoising Image Generation

How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective

no code implementations18 Apr 2024 Siyi Lin, Chongming Gao, Jiawei Chen, Sheng Zhou, Binbin Hu, Yan Feng, Chun Chen, Can Wang

Building on these insights, we propose a novel debiasing strategy that leverages a spectral norm regularizer to penalize the magnitude of the principal singular value.

Fairness Recommendation Systems

SIGformer: Sign-aware Graph Transformer for Recommendation

1 code implementation18 Apr 2024 Sirui Chen, Jiawei Chen, Sheng Zhou, Bohao Wang, Shen Han, Chanfei Su, Yuqing Yuan, Can Wang

Integrating both positive and negative feedback to form a signed graph can lead to a more comprehensive understanding of user preferences.

Recommendation Systems

Distributionally Robust Graph-based Recommendation System

1 code implementation20 Feb 2024 Bohao Wang, Jiawei Chen, Changdong Li, Sheng Zhou, Qihao Shi, Yang Gao, Yan Feng, Chun Chen, Can Wang

DR-GNN addresses two core challenges: 1) To enable DRO to cater to graph data intertwined with GNN, we reinterpret GNN as a graph smoothing regularizer, thereby facilitating the nuanced application of DRO; 2) Given the typically sparse nature of recommendation data, which might impede robust optimization, we introduce slight perturbations in the training distribution to expand its support.

Recommendation Systems

Knowledge Translation: A New Pathway for Model Compression

1 code implementation11 Jan 2024 Wujie Sun, Defang Chen, Jiawei Chen, Yan Feng, Chun Chen, Can Wang

Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead.

Data Augmentation Model Compression +1

StyleRetoucher: Generalized Portrait Image Retouching with GAN Priors

no code implementations22 Dec 2023 Wanchao Su, Can Wang, Chen Liu, Hangzhou Han, Hongbo Fu, Jing Liao

To address such issues, we present StyleRetoucher, a novel automatic portrait image retouching framework, leveraging StyleGAN's generation and generalization ability to improve an input portrait image's skin condition while preserving its facial details.

feature selection Image Retouching

Mesh-Guided Neural Implicit Field Editing

no code implementations4 Dec 2023 Can Wang, Mingming He, Menglei Chai, Dongdong Chen, Jing Liao

We first introduce a differentiable method using marching tetrahedra for polygonal mesh extraction from the neural implicit field and then design a differentiable color extractor to assign colors obtained from the volume renderings to this extracted mesh.

Fast ODE-based Sampling for Diffusion Models in Around 5 Steps

2 code implementations CVPR 2024 Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen

Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible.

Image Generation

Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction

no code implementations29 Nov 2023 Xinshun Wang, Wanying Zhang, Can Wang, Yuan Gao, Mengyuan Liu

Graph Convolutional Networks (GCN) which typically follows a neural message passing framework to model dependencies among skeletal joints has achieved high success in skeleton-based human motion prediction task.

Human motion prediction motion prediction

Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning

1 code implementation25 Sep 2023 Yang Liu, Chen Chen, Can Wang, Xulin King, Mengyuan Liu

The proposed method decouples functions between the decoder and the encoder by introducing a mask regressor, which predicts the masked patch representation from the visible patch representation encoded by the encoder and the decoder reconstructs the target from the predicted masked patch representation.

Decoder Few-Shot 3D Point Cloud Classification +2

CDR: Conservative Doubly Robust Learning for Debiased Recommendation

1 code implementation13 Aug 2023 Zijie Song, Jiawei Chen, Sheng Zhou, Qihao Shi, Yan Feng, Chun Chen, Can Wang

In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data.

Imputation Recommendation Systems

Customizing Synthetic Data for Data-Free Student Learning

1 code implementation10 Jul 2023 Shiya Luo, Defang Chen, Can Wang

Existing works generally synthesize data from the pre-trained teacher model to replace the original training data for student learning.

Data-free Knowledge Distillation

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

1 code implementation NeurIPS 2023 Zhiyao Zhou, Sheng Zhou, Bochao Mao, Xuanyi Zhou, Jiawei Chen, Qiaoyu Tan, Daochen Zha, Yan Feng, Chun Chen, Can Wang

Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption.

Graph structure learning Representation Learning

Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning

1 code implementation11 Jun 2023 Hailin Zhang, Defang Chen, Can Wang

Multi-Teacher knowledge distillation provides students with additional supervision from multiple pre-trained teachers with diverse information sources.

Knowledge Distillation Meta-Learning

A Geometric Perspective on Diffusion Models

2 code implementations31 May 2023 Defang Chen, Zhenyu Zhou, Jian-Ping Mei, Chunhua Shen, Chun Chen, Can Wang

Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models.

Denoising

Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields

1 code implementation19 May 2023 Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao

Extensive experiments demonstrate that our Text2NeRF outperforms existing methods in producing photo-realistic, multi-view consistent, and diverse 3D scenes from a variety of natural language prompts.

3D Generation 3D Reconstruction +4

AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control

1 code implementation ICCV 2023 Ruixiang Jiang, Can Wang, Jingbo Zhang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

Neural implicit fields are powerful for representing 3D scenes and generating high-quality novel views, but it remains challenging to use such implicit representations for creating a 3D human avatar with a specific identity and artistic style that can be easily animated.

Jointly Complementary&Competitive Influence Maximization with Concurrent Ally-Boosting and Rival-Preventing

no code implementations19 Feb 2023 Qihao Shi, Wenjie Tian, Wujian Yang, Mengqi Xue, Can Wang, Minghui Wu

In this paper, we propose a new influence spread model, namely, Complementary\&Competitive Independent Cascade (C$^2$IC) model.

Blocking

Robust Sequence Networked Submodular Maximization

no code implementations28 Dec 2022 Qihao Shi, Bingyang Fu, Can Wang, Jiawei Chen, Sheng Zhou, Yan Feng, Chun Chen

The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology.

Link Prediction

NeRF-Art: Text-Driven Neural Radiance Fields Stylization

1 code implementation15 Dec 2022 Can Wang, Ruixiang Jiang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

As a powerful representation of 3D scenes, the neural radiance field (NeRF) enables high-quality novel view synthesis from multi-view images.

Contrastive Learning Novel View Synthesis

Accelerating Diffusion Sampling with Classifier-based Feature Distillation

1 code implementation22 Nov 2022 Wujie Sun, Defang Chen, Can Wang, Deshi Ye, Yan Feng, Chun Chen

Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance.

Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervision

no code implementations25 Oct 2022 Jiongyu Guo, Defang Chen, Can Wang

Alignahead++ transfers structure and feature information in a student layer to the previous layer of another simultaneously trained student model in an alternating training procedure.

Knowledge Distillation Model Compression

FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing

1 code implementation11 Aug 2022 Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao

Unlike existing dynamic NeRFs that require dense images as input and can only be modeled for a single identity, our method enables face reconstruction across different persons with few-shot inputs.

3D Face Reconstruction

Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding

no code implementations7 Jun 2022 Yichen Liu, Jiawei Chen, Defang Chen, Zhehui Zhou, Yan Feng, Can Wang

Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, have garnered significant attention.

Knowledge Graph Embedding Knowledge Graphs +3

Alignahead: Online Cross-Layer Knowledge Extraction on Graph Neural Networks

1 code implementation5 May 2022 Jiongyu Guo, Defang Chen, Can Wang

Existing knowledge distillation methods on graph neural networks (GNNs) are almost offline, where the student model extracts knowledge from a powerful teacher model to improve its performance.

Knowledge Distillation

Knowledge Distillation with the Reused Teacher Classifier

1 code implementation CVPR 2022 Defang Chen, Jian-Ping Mei, Hailin Zhang, Can Wang, Yan Feng, Chun Chen

Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance.

Knowledge Distillation

Knowledge Distillation with Deep Supervision

no code implementations16 Feb 2022 Shiya Luo, Defang Chen, Can Wang

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model.

Knowledge Distillation Transfer Learning

Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization

no code implementations ICLR 2022 Can Wang, Sheng Jin, Yingda Guan, Wentao Liu, Chen Qian, Ping Luo, Wanli Ouyang

PL approaches apply pseudo-labels to unlabeled data, and then train the model with a combination of the labeled and pseudo-labeled data iteratively.

Confidence-Aware Multi-Teacher Knowledge Distillation

1 code implementation30 Dec 2021 Hailin Zhang, Defang Chen, Can Wang

Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training.

Knowledge Distillation Transfer Learning

Online Adversarial Distillation for Graph Neural Networks

no code implementations28 Dec 2021 Can Wang, Zhe Wang, Defang Chen, Sheng Zhou, Yan Feng, Chun Chen

However, its effect on graph neural networks is less than satisfactory since the graph topology and node attributes are likely to change in a dynamic way and in this case a static teacher model is insufficient in guiding student training.

Knowledge Distillation

CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields

2 code implementations CVPR 2022 Can Wang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

Furthermore, we propose an inverse optimization method that accurately projects an input image to the latent codes for manipulation to enable editing on real images.

Novel View Synthesis

Distilling Holistic Knowledge with Graph Neural Networks

1 code implementation ICCV 2021 Sheng Zhou, Yucheng Wang, Defang Chen, Jiawei Chen, Xin Wang, Can Wang, Jiajun Bu

The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner.

Knowledge Distillation

Deep Portrait Lighting Enhancement with 3D Guidance

no code implementations4 Aug 2021 Fangzhou Han, Can Wang, Hao Du, Jing Liao

To address this, we present a novel deep learning framework for portrait lighting enhancement based on 3D facial guidance.

Image-to-Image Translation Translation

Human Pose Regression with Residual Log-likelihood Estimation

3 code implementations ICCV 2021 Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, Cewu Lu

In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution.

3D Human Pose Estimation Multi-Person Pose Estimation +1

Cross-Domain and Disentangled Face Manipulation with 3D Guidance

1 code implementation22 Apr 2021 Can Wang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability.

Attribute Domain Adaptation +1

Cross-Layer Distillation with Semantic Calibration

2 code implementations6 Dec 2020 Defang Chen, Jian-Ping Mei, Yuan Zhang, Can Wang, Yan Feng, Chun Chen

Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model.

Knowledge Distillation Transfer Learning

SamWalker++: recommendation with informative sampling strategy

1 code implementation16 Nov 2020 Can Wang, Jiawei Chen, Sheng Zhou, Qihao Shi, Yan Feng, Chun Chen

However, the social network information may not be available in many recommender systems, which hinders application of SamWalker.

Recommendation Systems

CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation

no code implementations16 Nov 2020 Jiawei Chen, Chengquan Jiang, Can Wang, Sheng Zhou, Yan Feng, Chun Chen, Martin Ester, Xiangnan He

To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling.

Recommendation Systems

TRec: Sequential Recommender Based On Latent Item Trend Information

no code implementations11 Sep 2020 Ye Tao, Can Wang, Lina Yao, Weimin Li, Yonghong Yu

Our study demonstrates the importance of item trend information in recommendation system designs, and our method also possesses great efficiency which enables it to be practical in real-world scenarios.

Sequential Recommendation

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

no code implementations ECCV 2020 Jiefeng Li, Can Wang, Wentao Liu, Chen Qian, Cewu Lu

The HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically, which captures the body-part and joint level semantic and maintains global consistency at the same time.

3D Multi-Person Pose Estimation (absolute) 3D Multi-Person Pose Estimation (root-relative) +2

Whole-Body Human Pose Estimation in the Wild

2 code implementations ECCV 2020 Sheng Jin, Lumin Xu, Jin Xu, Can Wang, Wentao Liu, Chen Qian, Wanli Ouyang, Ping Luo

This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet.

2D Human Pose Estimation Facial Landmark Detection +2

Spectrum-Guided Adversarial Disparity Learning

1 code implementation14 Jul 2020 Zhe Liu, Lina Yao, Lei Bai, Xianzhi Wang, Can Wang

It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class.

Activity Recognition Denoising

Pose-aware Adversarial Domain Adaptation for Personalized Facial Expression Recognition

no code implementations12 Jul 2020 Guang Liang, Shangfei Wang, Can Wang

The first aims to learn pose- and expression-related feature representations in the source domain and adapt both feature distributions to that of the target domain by imposing adversarial learning.

Disentanglement Domain Adaptation +2

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

3 code implementations NeurIPS 2020 Lei Bai, Lina Yao, Can Li, Xianzhi Wang, Can Wang

We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks.

Graph Generation Graph Neural Network +5

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback

no code implementations4 Mar 2020 Jiawei Chen, Can Wang, Sheng Zhou, Qihao Shi, Jingbang Chen, Yan Feng, Chun Chen

A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence.

Online Knowledge Distillation with Diverse Peers

2 code implementations1 Dec 2019 Defang Chen, Jian-Ping Mei, Can Wang, Yan Feng, Chun Chen

The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i. e., the model used for inference.

Knowledge Distillation Transfer Learning

Hierarchical Graph Pooling with Structure Learning

3 code implementations14 Nov 2019 Zhen Zhang, Jiajun Bu, Martin Ester, Jianfeng Zhang, Chengwei Yao, Zhi Yu, Can Wang

HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs.

Graph Classification Graph Neural Network +1

An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE

no code implementations22 May 2019 Tianye Zhang, Haozhe Feng, Zexian Chen, Can Wang, Yanhao Huang, Yong Tang, Wei Chen

Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid.

HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding

2 code implementations31 Jan 2019 Sheng Zhou, Jiajun Bu, Xin Wang, Jia-Wei Chen, Can Wang

Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space.

Network Embedding

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark

3 code implementations CVPR 2019 Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu

In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms.

Keypoint Detection Multi-Person Pose Estimation

Multi-modality Sensor Data Classification with Selective Attention

no code implementations16 Apr 2018 Xiang Zhang, Lina Yao, Chaoran Huang, Sen Wang, Mingkui Tan, Guodong Long, Can Wang

Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment.

Classification General Classification

Navigation Objects Extraction for Better Content Structure Understanding

no code implementations26 Aug 2017 Kui Zhao, Bangpeng Li, Zilun Peng, Jiajun Bu, Can Wang

Dynamic and personalized elements such as top stories, recommended list in a webpage are vital to the understanding of the dynamic nature of web 2. 0 sites.

Deep Style Match for Complementary Recommendation

no code implementations26 Aug 2017 Kui Zhao, Xia Hu, Jiajun Bu, Can Wang

In order to answer these kinds of questions, we attempt to model human sense of style compatibility in this paper.

Common Sense Reasoning Feature Engineering

Sales Forecast in E-commerce using Convolutional Neural Network

no code implementations26 Aug 2017 Kui Zhao, Can Wang

To overcome the limitations of existing methods, we propose a novel approach in this paper to learn effective features automatically from the structured data using the Convolutional Neural Network (CNN).

Feature Engineering

Orientation Driven Bag of Appearances for Person Re-identification

2 code implementations9 May 2016 Liqian Ma, Hong Liu, Liang Hu, Can Wang, Qianru Sun

Experimental results on three public datasets and two proposed datasets demonstrate the superiority of the proposed approach, indicating the effectiveness of body structure and orientation information for improving re-identification performance.

Person Re-Identification

Binary Tree based Chinese Word Segmentation

no code implementations17 May 2013 Kaixu Zhang, Can Wang, Maosong Sun

A binary tree based framework is also designed to overcome the granularity mismatch problem.

Chinese Word Segmentation Segmentation

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