1 code implementation • 13 Apr 2022 • Haiming Yu, Hao Zhu, Xiangju Lu, Junhui Liu
In this work, we propose MobileFSGAN, a novel lightweight GAN for face swap that can run on mobile devices with much fewer parameters while achieving competitive performance.
no code implementations • 1 Apr 2022 • Yaning Li, Xue Wang, Hao Zhu, Guoqing Zhou, Qing Wang
Existing light field representations, such as epipolar plane image (EPI) and sub-aperture images, do not consider the structural characteristics across the views, so they usually require additional disparity and spatial structure cues for follow-up tasks.
no code implementations • 25 Mar 2022 • Xinmeng Li, Hao Zhu, Li-Ping Liu, Soha Hassoun
We show that annotation performance, for ESP and other models, is a strong function of the number of molecules in the candidate set and their similarity to the target molecule.
no code implementations • 24 Mar 2022 • Jialin Wang, Rui Gao, Haotian Zheng, Hao Zhu, C. -J. Richard Shi
Compared with the existing literature, our WNFG of EEG signals achieves up to 10 times of redundant edge reduction, and our approach achieves up to 97 times of model pruning without loss of classification accuracy.
no code implementations • 13 Feb 2022 • Yifei Zhang, Hao Zhu, Ziqiao Meng, Piotr Koniusz, Irwin King
However, in the updating stage, all nodes share the same updating function.
1 code implementation • NeurIPS 2021 • Hao Zhu, Ke Sun, Piotr Koniusz
Starting from a GAN-inspired contrastive formulation, we show that the Jensen-Shannon divergence underlying many contrastive graph embedding models fails under disjoint positive and negative distributions, which may naturally emerge during sampling in the contrastive setting.
1 code implementation • 4 Jan 2022 • Yunze Xiao, Hao Zhu, Haotian Yang, Zhengyu Diao, Xiangju Lu, Xun Cao
By fitting a 3D morphable model from multi-view images, the features of multiple images are extracted and aggregated in the mesh-attached UV space, which makes the implicit function more effective in recovering detailed facial shape.
1 code implementation • 4 Dec 2021 • Yiyu Zhuang, Hao Zhu, Xusen Sun, Xun Cao
Specifically, MoFaNeRF takes the coded facial shape, expression and appearance along with space coordinate and view direction as input to an MLP, and outputs the radiance of the space point for photo-realistic image synthesis.
no code implementations • 23 Nov 2021 • Yuqi Zhou, Arun Sukumaran Nair, David Ganger, Abhinandan Tripathi, Chaitanya Baone, Hao Zhu
Accurate load forecasting is critical for electricity market operations and other real-time decision-making tasks in power systems.
no code implementations • 23 Nov 2021 • Yuqi Zhou, Jeehyun Park, Hao Zhu
Effective and timely responses to unexpected contingencies are crucial for enhancing the resilience of power grids.
1 code implementation • 1 Nov 2021 • Hao Zhu, Haotian Yang, Longwei Guo, Yidi Zhang, Yanru Wang, Mingkai Huang, Qiu Shen, Ruigang Yang, Xun Cao
By training on FaceScape data, a novel algorithm is proposed to predict elaborate riggable 3D face models from a single image input.
no code implementations • 14 Oct 2021 • Lintao Ye, Hao Zhu, Vijay Gupta
We study the problem of control policy design for decentralized state-feedback linear quadratic control with a partially nested information structure, when the system model is unknown.
1 code implementation • 4 Oct 2021 • Shanny Lin, Shaohui Liu, Hao Zhu
Real-time coordination of distributed energy resources (DERs) is crucial for regulating the voltage profile in distribution grids.
no code implementations • 29 Sep 2021 • Hao Zhu, Mahashweta Das, Mangesh Bendre, Fei Wang, Hao Yang, Soha Hassoun
In this work, we propose an adversarial training based modification to the current state-of-the-arts link prediction method to solve this problem.
1 code implementation • CoNLL (EMNLP) 2021 • Ruisi Su, Shruti Rijhwani, Hao Zhu, Junxian He, Xinyu Wang, Yonatan Bisk, Graham Neubig
Our experiments find that concreteness is a strong indicator for learning dependency grammars, improving the direct attachment score (DAS) by over 50\% as compared to state-of-the-art models trained on pure text.
no code implementations • 24 Aug 2021 • Hao Zhu, Piotr Koniusz
Moreover, we design a simple but efficient spectral filter for network enhancement to obtain higher-order information for node representation.
1 code implementation • 20 Aug 2021 • Xiaopeng Lu, Lynnette Ng, Jared Fernandez, Hao Zhu
Instead of generating an image based on text as in text-image generation, this task requires the generation of an image from a textual description and an image prompt.
no code implementations • 18 Aug 2021 • Shanny Lin, Hao Zhu
Accurately modeling power distribution grids is crucial for designing effective monitoring and decision making algorithms.
no code implementations • 7 Aug 2021 • Kyung-bin Kwon, Hao Zhu
Effectively operating electrical vehicle charging station (EVCS) is crucial for enabling the rapid transition of electrified transportation.
no code implementations • 6 Aug 2021 • Hao Zhu, Xinxin Zuo, Haotian Yang, Sen Wang, Xun Cao, Ruigang Yang
In this paper, we propose a novel learning-based framework that combines the robustness of the parametric model with the flexibility of free-form 3D deformation.
no code implementations • 24 Jul 2021 • Hao Zhu, Piotr Koniusz
Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are still using linear transformations and a simple pooling step.
no code implementations • 12 Jul 2021 • Hao Zhu, Graham Neubig, Yonatan Bisk
Positive results from our experiments hint at the importance of explicitly modeling communication as a socio-pragmatic progress.
1 code implementation • 19 Jun 2021 • Shaohui Liu, Chengyang Wu, Hao Zhu
Solving the optimal power flow (OPF) problem in real-time electricity market improves the efficiency and reliability in the integration of low-carbon energy resources into the power grids.
no code implementations • 26 May 2021 • Mana Jalali, Vassilis Kekatos, Siddharth Bhela, Hao Zhu, Virgilio Centeno
Synchrophasor data provide unprecedented opportunities for inferring power system dynamics, such as estimating voltage angles, frequencies, and accelerations along with power injection at all buses.
1 code implementation • 12 Apr 2021 • Shaohui Liu, Hao Zhu, Vassilis Kekatos
Wide-area dynamic studies are of paramount importance to ensure the stability and reliability of power grids.
no code implementations • 15 Feb 2021 • Shanny Lin, Hao Zhu
The load recovery solutions can be utilized to identify the EV charging events at each load node and to infer the total behind-the-meter PV output.
no code implementations • 23 Jan 2021 • Yaning Li, Xue Wang, Hao Zhu, Guoqing Zhou, Qing Wang
Based on these two observations, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack.
2 code implementations • ICLR 2021 • Hao Zhu, Piotr Koniusz
Our spectral analysis shows that our simple spectral graph convolution used in S^2GC is a low-pass filter which partitions networks into a few large parts.
Ranked #1 on
Text Classification
on 20NEWS
no code implementations • 23 Nov 2020 • Hao Zhu, Yang Yuan, Guosheng Hu, Xiang Wu, Neil Robertson
IR-Softmax can generalise to any softmax and its variants (which are discriminative for open-set problem) by directly setting the weights as their class centers, naturally solving the data imbalance problem.
no code implementations • NeurIPS 2020 • Hao Zhu, Chaoyou Fu, Qianyi Wu, Wayne Wu, Chen Qian, Ran He
However, due to the lack of Deepfakes datasets with large variance in appearance, which can be hardly produced by recent identity swapping methods, the detection algorithm may fail in this situation.
no code implementations • 5 Nov 2020 • Hao Zhu, Yi Li, Feixia Zhu, Aihua Zheng, Ran He
We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip.
1 code implementation • NeurIPS 2020 • Nitin Kamra, Hao Zhu, Dweep Trivedi, Ming Zhang, Yan Liu
Trajectory prediction for scenes with multiple agents and entities is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning.
no code implementations • 9 Oct 2020 • Hao Zhu, LiPing Liu, Soha Hassoun
We compare our results to NEIMS, a neural network model that utilizes molecular fingerprints as inputs.
3 code implementations • 29 Jul 2020 • Hao Zhu, Yonatan Bisk, Graham Neubig
In this paper we demonstrate that $\textit{context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies}$.
1 code implementation • 17 Jul 2020 • Miao Liao, Sibo Zhang, Peng Wang, Hao Zhu, Xinxin Zuo, Ruigang Yang
In this paper, we propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person, where the output video has synchronized, realistic, and expressive rich body dynamics.
no code implementations • 14 Jul 2020 • Yifei Zhang, Hao Zhu
For this scheme, we propose a novel privacy-preserving architecture where two parties can collaboratively train a deep learning model efficiently while preserving the privacy of each party's data.
1 code implementation • CVPR 2020 • Feitong Tan, Hao Zhu, Zhaopeng Cui, Siyu Zhu, Marc Pollefeys, Ping Tan
Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data.
1 code implementation • CVPR 2020 • Haotian Yang, Hao Zhu, Yanru Wang, Mingkai Huang, Qiu Shen, Ruigang Yang, Xun Cao
In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and propose a novel algorithm that is able to predict elaborate riggable 3D face models from a single image input.
1 code implementation • CVPR 2020 • Fanbo Xiang, Yuzhe Qin, Kaichun Mo, Yikuan Xia, Hao Zhu, Fangchen Liu, Minghua Liu, Hanxiao Jiang, Yifu Yuan, He Wang, Li Yi, Angel X. Chang, Leonidas J. Guibas, Hao Su
To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable.
no code implementations • 14 Jan 2020 • Hao Zhu, Mandi Luo, Rui Wang, Aihua Zheng, Ran He
Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully.
no code implementations • 23 Dec 2019 • Yuxiang Ren, Hao Zhu, Jiawei Zhang, Peng Dai, Liefeng Bo
Existing fraud detection methods try to identify unexpected dense subgraphs and treat related nodes as suspicious.
no code implementations • 31 Oct 2019 • Yuzhe Qin, Rui Chen, Hao Zhu, Meng Song, Jing Xu, Hao Su
Grasping is among the most fundamental and long-lasting problems in robotics study.
1 code implementation • IJCNLP 2019 • Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie zhou
We present FewRel 2. 0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances?
2 code implementations • 26 Sep 2019 • Jianqiang Wang, Hao Zhu, Zhan Ma, Tong Chen, Haojie Liu, Qiu Shen
This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a. k. a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE).
1 code implementation • ACL 2019 • Weize Chen, Hao Zhu, Xu Han, Zhiyuan Liu, Maosong Sun
We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases.
2 code implementations • 22 Jun 2019 • Weiping Song, Zhijian Duan, Ziqing Yang, Hao Zhu, Ming Zhang, Jian Tang
Recently, a variety of methods have been developed for this problem, which generally try to learn effective representations of users and items and then match items to users according to their representations.
Ranked #1 on
Recommendation Systems
on Last.FM
no code implementations • 19 Jun 2019 • Kaiqing Zhang, Alec Koppel, Hao Zhu, Tamer Başar
Under a further strict saddle points assumption, this result establishes convergence to essentially locally-optimal policies of the underlying problem, and thus bridges the gap in existing literature on the convergence of PG methods.
no code implementations • NAACL 2019 • Chu-Cheng Lin, Hao Zhu, Matthew R. Gormley, Jason Eisner
We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings.
1 code implementation • NAACL 2019 • Yifei Zhang, Hao Zhu
However, the discrete stochastic layer is usually incompatible with the backpropagation in the training stage, and thus causes a gradient flow problem because of non-differentiable operators.
1 code implementation • CVPR 2019 • Hao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang
This paper presents a novel framework to recover detailed human body shapes from a single image.
no code implementations • 15 Feb 2019 • Hao Zhu, Mantang Guo, Hongdong Li, Qing Wang, Antonio Robles-Kelly
We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.
1 code implementation • ACL 2019 • Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-Seng Chua, Maosong Sun
Recently, progress has been made towards improving relational reasoning in machine learning field.
no code implementations • 17 Dec 2018 • Hao Zhu, Huaibo Huang, Yi Li, Aihua Zheng, Ran He
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.
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.
Ranked #6 on
Multi-Person Pose Estimation
on CrowdPose
1 code implementation • EMNLP 2018 • Yihong Gu, Jun Yan, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin
Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words.
1 code implementation • EMNLP 2018 • Xu Han, Hao Zhu, Pengfei Yu, ZiYun Wang, Yuan YAO, Zhiyuan Liu, Maosong Sun
The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers.
1 code implementation • EMNLP 2018 • Ji Xin, Hao Zhu, Xu Han, Zhiyuan Liu, Maosong Sun
Entity typing aims to classify semantic types of an entity mention in a specific context.
1 code implementation • EMNLP 2018 • Fanchao Qi, Yankai Lin, Maosong Sun, Hao Zhu, Ruobing Xie, Zhiyuan Liu
We propose a novel framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction.
1 code implementation • ACL 2018 • Huiming Jin, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin
However, existing methods of lexical sememe prediction typically rely on the external context of words to represent the meaning, which usually fails to deal with low-frequency and out-of-vocabulary words.
no code implementations • 14 Jun 2018 • Mantang Guo, Hao Zhu, Guoqing Zhou, Qing Wang
A light field records numerous light rays from a real-world scene.
no code implementations • CVPR 2018 • Hao Zhu, Hao Su, Peng Wang, Xun Cao, Ruigang Yang
We study how to synthesize novel views of human body from a single image.
no code implementations • 3 Jan 2018 • Zhiwu Lin, Jincheng Yang, Hao Zhu
The second one is to write the linearized fluid equation in a Hamiltonian form and then use an instability index theory for general Hamiltonian PDEs.
Analysis of PDEs
no code implementations • 20 Dec 2017 • Xianqiang Lv, Hao Zhu, Qing Wang
The large volume of input data and the redundancy of light field make it an open challenge.
no code implementations • CVPR 2017 • Hao Zhu, Qi Zhang, Qing Wang
Superpixel segmentation of 2D image has been widely used in many computer vision tasks.
1 code implementation • International Joint Conference on Artificial Intelligence 2017 • Hao Zhu, Ruobing Xie, Zhiyuan Liu, Maosong Sun
During this process, we can align entities according to their semantic distance in this joint semantic space.
no code implementations • 15 Aug 2016 • Hao Zhu, Qing Wang, Jingyi Yu
Occlusion is one of the most challenging problems in depth estimation.
no code implementations • 30 Mar 2015 • Georgios B. Giannakis, Qing Ling, Gonzalo Mateos, Ioannis D. Schizas, Hao Zhu
This chapter deals with decentralized learning algorithms for in-network processing of graph-valued data.