Search Results for author: Peng He

Found 15 papers, 5 papers with code

Micro Expression Generation with Thin-plate Spline Motion Model and Face Parsing

3 code implementations MM '22: Proceedings of the 30th ACM International Conference on Multimedia 2022 Jun Yu, Guochen Xie, Zhongpeng Cai, Peng He, Fang Gao, Qiang Ling

We (Team: USTC-IAT-United) also compare our method with other competitors' in MEGC2022, and the expert evaluation results show that our method performs best, which verifies the effectiveness of our method.

Face Parsing Micro-expression Generation +2

Spectral2Spectral: Image-spectral Similarity Assisted Spectral CT Deep Reconstruction without Reference

no code implementations3 Oct 2022 Xiaodong Guo, Longhui Li, Dingyue Chang, Peng He, Peng Feng, Hengyong Yu, Weiwen Wu

Spectral computed tomography based on a photon-counting detector (PCD) attracts more and more attentions since it has the capability to provide more accurate identification and quantitative analysis for biomedical materials.

Network Pruning via Feature Shift Minimization

1 code implementation6 Jul 2022 Yuanzhi Duan, Yue Zhou, Peng He, Qiang Liu, Shukai Duan, Xiaofang Hu

In this paper, we propose a novel Feature Shift Minimization (FSM) method to compress CNN models, which evaluates the feature shift by converging the information of both features and filters.

Network Pruning

Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions

no code implementations5 Jun 2022 Peng He

All these clues allow us to discover a novel geometric picture of nonconvex optimization in deep learning: angular distribution in high-dimensional data space $\mapsto$ spectrums of overparameterized activation matrices $\mapsto$ favorable geometrical properties of empirical loss landscape $\mapsto$ global convergence phenomenon.

Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation

no code implementations30 Mar 2022 Hao Chen, Zhong Huang, Yue Xu, Zengde Deng, Feiran Huang, Peng He, Zhoujun Li

The experimental results verify that our proposed NEGCN framework can significantly enhance the performance for various typical GCN models on both node classification and recommendation tasks.

Classification Node Classification

Multi-model Ensemble Learning Method for Human Expression Recognition

no code implementations28 Mar 2022 Jun Yu, Zhongpeng Cai, Peng He, Guocheng Xie, Qiang Ling

Moreover, we introduce the multi-fold ensemble method to train and ensemble several models with the same architecture but different data distributions to enhance the performance of our solution.

Ensemble Learning

Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph

no code implementations30 Apr 2021 Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen

We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.

Click-Through Rate Prediction Knowledge Graph Embedding +1

Geometry and superfluidity of the flat band in a non-Hermitian optical lattice

no code implementations4 Jan 2021 Peng He, Hai-Tao Ding, Shi-Liang Zhu

We propose an ultracold-atom setting where a fermionic superfluidity with attractive s-wave interaction is uploaded in a non-Hermitian Lieb optical lattice.

Quantum Gases Mesoscale and Nanoscale Physics Superconductivity Quantum Physics

Single-Layer Graph Convolutional Networks For Recommendation

no code implementations7 Jun 2020 Yue Xu, Hao Chen, Zengde Deng, Junxiong Zhu, Yanghua Li, Peng He, Wenyao Gao, Wenjun Xu

The results verify that the proposed model outperforms existing GCN models considerably and yields up to a few orders of magnitude speedup in training, in terms of the recommendation performance.

Recommendation Systems

SocialTrans: A Deep Sequential Model with Social Information for Web-Scale Recommendation Systems

no code implementations9 May 2020 Qiaoan Chen, Hao Gu, Lingling Yi, Yishi Lin, Peng He, Chuan Chen, Yangqiu Song

Experiments on three data sets verify the effectiveness of our model and show that it outperforms state-of-the-art social recommendation methods.

Graph Attention Recommendation Systems

Learning Enhanced Resolution-wise features for Human Pose Estimation

no code implementations11 Sep 2019 Kun Zhang, Peng He, Ping Yao, Ge Chen, Rui Wu, Min Du, Huimin Li, Li Fu, Tianyao Zheng

Specifically, RAM learns a group of weights to represent the different importance of feature maps across resolutions, and the GPR gradually merges every two feature maps from low to high resolutions to regress final human keypoint heatmaps.

GPR Keypoint Detection +1

Label-Aware Graph Convolutional Networks

no code implementations10 Jul 2019 Hao Chen, Yue Xu, Feiran Huang, Zengde Deng, Wenbing Huang, Senzhang Wang, Peng He, Zhoujun Li

In this paper, we consider the problem of node classification and propose the Label-Aware Graph Convolutional Network (LAGCN) framework which can directly identify valuable neighbors to enhance the performance of existing GCN models.

General Classification Graph Classification +2

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