Search Results for author: ZiHao Wang

Found 43 papers, 8 papers with code

Posterior Collapse of a Linear Latent Variable Model

no code implementations9 May 2022 ZiHao Wang, Liu Ziyin

This work identifies the existence and cause of a type of posterior collapse that frequently occurs in the Bayesian deep learning practice.

Surface Reconstruction from Point Clouds: A Survey and a Benchmark

no code implementations5 May 2022 Zhangjin Huang, Yuxin Wen, ZiHao Wang, Jinjuan Ren, Kui Jia

For example, while deep learning methods are increasingly popular, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods.

Surface Reconstruction

Query2Particles: Knowledge Graph Reasoning with Particle Embeddings

1 code implementation27 Apr 2022 Jiaxin Bai, ZiHao Wang, Hongming Zhang, Yangqiu Song

The query embedding method is proposed to answer these queries by jointly encoding queries and entities to the same embedding space.

Entity Embeddings Knowledge Graphs

A Neural-Symbolic Approach to Natural Language Understanding

no code implementations20 Mar 2022 Zhixuan Liu, ZiHao Wang, Yuan Lin, Hang Li

Inspired by the theory, we present a novel framework for NLU called Neural-Symbolic Processor (NSP), which performs analogical reasoning based on neural processing and performs logical reasoning based on both neural and symbolic processing.

Natural Language Inference Natural Language Understanding +1

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

no code implementations8 Mar 2022 Yongwei Chen, ZiHao Wang, Longkun Zou, Ke Chen, Kui Jia

Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models.

Point Cloud Classification Unsupervised Domain Adaptation

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

2 code implementations1 Mar 2022 ZiHao Wang, Wei Liu, Qian He, Xinglong Wu, Zili Yi

Once trained, the transformer can generate coherent image tokens based on the text embedding extracted from the text encoder of CLIP upon an input text.

Text to image generation Text-to-Image Generation

A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generation

no code implementations13 Oct 2021 ZiHao Wang, Ming Jiang, Junli Wang

Differing from prior work that solely relies on the content of conversation history to generate a response, we argue that capturing relative social relations among utterances (i. e., generated by either the same speaker or different persons) benefits the machine capturing fine-grained context information from a conversation history to improve context coherence in the generated response.

Dialogue Generation

Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs

2 code implementations18 Sep 2021 ZiHao Wang, Hang Yin, Yangqiu Song

Besides, our work, for the first time, provides a benchmark to evaluate and analyze the impact of different operators and normal forms by using (a) 7 choices of the operator systems and (b) 9 forms of complex queries.

Knowledge Graphs

Economic Recession Prediction Using Deep Neural Network

no code implementations21 Jul 2021 ZiHao Wang, Kun Li, Steve Q. Xia, Hongfu Liu

We investigate the effectiveness of different machine learning methodologies in predicting economic cycles.

Non-negative matrix factorization algorithms greatly improve topic model fits

1 code implementation27 May 2021 Peter Carbonetto, Abhishek Sarkar, ZiHao Wang, Matthew Stephens

We report on the potential for using algorithms for non-negative matrix factorization (NMF) to improve parameter estimation in topic models.

Topic Models Variational Inference

Attention for Image Registration (AiR): an unsupervised Transformer approach

no code implementations5 May 2021 ZiHao Wang, Hervé Delingette

In a more vivid interpretation: we treat the image registration problem as the same as a language translation task and introducing a Transformer to tackle the problem.

Image Registration

Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild

no code implementations18 Jan 2021 Shivam Duggal, ZiHao Wang, Wei-Chiu Ma, Sivabalan Manivasagam, Justin Liang, Shenlong Wang, Raquel Urtasun

Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics.

3D Object Reconstruction

Adaptive Tree Wasserstein Minimization for Hierarchical Generative Modeling

no code implementations1 Jan 2021 ZiHao Wang, Xu Zhao, Tam Le, Hao Wu, Yong Zhang, Makoto Yamada

In this work, we consider OT over tree metrics, which is more general than the sliced Wasserstein and includes the sliced Wasserstein as a special case, and we propose a fast minimization algorithm in $O(n)$ for the optimal Wasserstein-1 transport plan between two distributions in the tree structure.

Unsupervised Domain Adaptation

PV-NAS: Practical Neural Architecture Search for Video Recognition

no code implementations2 Nov 2020 ZiHao Wang, Chen Lin, Lu Sheng, Junjie Yan, Jing Shao

Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability.

Neural Architecture Search Video Recognition

Long Short-Term Memory Neuron Equalizer

no code implementations27 Oct 2020 ZiHao Wang, Zhifei Xu, Jiayi He, Chulsoon Hwang, Jun Fan, Hervé Delingette

In this work we propose a neuromorphic hardware based signal equalizer by based on the deep learning implementation.

An Investigation of how Label Smoothing Affects Generalization

no code implementations23 Oct 2020 Blair Chen, Liu Ziyin, ZiHao Wang, Paul Pu Liang

In this paper, as a step towards understanding why label smoothing is effective, we propose a theoretical framework to show how label smoothing provides in controlling the generalization loss.

Feature matching in Ultrasound images

no code implementations23 Oct 2020 Hang Zhu, ZiHao Wang

Feature matching is an important technique to identify a single object in different images.

Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction

1 code implementation EMNLP 2020 Xu Zhao, ZiHao Wang, Hao Wu, Yong Zhang

In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment.

Bilingual Lexicon Induction

A Relaxed Matching Procedure for Unsupervised BLI

no code implementations ACL 2020 Xu Zhao, ZiHao Wang, Hao Wu, Yong Zhang

Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest.

Bilingual Lexicon Induction Translation

Emora: An Inquisitive Social Chatbot Who Cares For You

no code implementations10 Sep 2020 Sarah E. Finch, James D. Finch, Ali Ahmadvand, Ingyu, Choi, Xiangjue Dong, Ruixiang Qi, Harshita Sahijwani, Sergey Volokhin, Zihan Wang, ZiHao Wang, Jinho D. Choi

Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI.

Chatbot Intent Classification

Quasi-symplectic Langevin Variational Autoencoder

no code implementations2 Sep 2020 Zihao Wang, Hervé Delingette

The HVAE adapted the Hamiltonian dynamic flow into variational inference that significantly improves the performance of the posterior estimation.

Variational Inference

Weakly-supervised 3D Shape Completion in the Wild

no code implementations ECCV 2020 Jiayuan Gu, Wei-Chiu Ma, Sivabalan Manivasagam, Wenyuan Zeng, ZiHao Wang, Yuwen Xiong, Hao Su, Raquel Urtasun

3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned.

Point Cloud Registration Pose Estimation

Fully Automated Segmentation of the Left Ventricle in Magnetic Resonance Images

no code implementations21 Jul 2020 ZiHao Wang, ZhenZhou Wang

We also proposed a fully automated LV segmentation method based on slope difference distribution (SDD) threshold selection to compare with the reproduced CNN methods.

Classification General Classification +1

A Deep Learning based Fast Signed Distance Map Generation

no code implementations MIDL 2019 Zihao Wang, Clair Vandersteen, Thomas Demarcy, Dan Gnansia, Charles Raffaelli, Nicolas Guevara, Hervé Delingette

Signed distance map (SDM) is a common representation of surfaces in medical image analysis and machine learning.

Volumization as a Natural Generalization of Weight Decay

no code implementations25 Mar 2020 Liu Ziyin, ZiHao Wang, Makoto Yamada, Masahito Ueda

We propose a novel regularization method, called \textit{volumization}, for neural networks.

End-To-End Graph-based Deep Semi-Supervised Learning

no code implementations23 Feb 2020 Zihao Wang, Enmei Tu, Zhou Meng

The quality of a graph is determined jointly by three key factors of the graph: nodes, edges and similarity measure (or edge weights), and is very crucial to the success of graph-based semi-supervised learning (SSL) approaches.

Semantic Similarity Semantic Textual Similarity

Structural-Aware Sentence Similarity with Recursive Optimal Transport

no code implementations28 Jan 2020 Zihao Wang, Yong Zhang, Hao Wu

Moreover, we further develop Recursive Optimal Similarity (ROTS) for sentences with the valuable semantic insights from the connections between cosine similarity of weighted average of word vectors and optimal transport.

Sentence Similarity

Higher-order Weighted Graph Convolutional Networks

no code implementations11 Nov 2019 Songtao Liu, Lingwei Chen, Hanze Dong, ZiHao Wang, Dinghao Wu, Zengfeng Huang

Graph Convolution Network (GCN) has been recognized as one of the most effective graph models for semi-supervised learning, but it extracts merely the first-order or few-order neighborhood information through information propagation, which suffers performance drop-off for deeper structure.

Node Classification

Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion

no code implementations IJCNLP 2019 Zihao Wang, Kwun Ping Lai, Piji Li, Lidong Bing, Wai Lam

Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions.

Few-Shot Learning Knowledge Graph Completion

Wasserstein-Fisher-Rao Document Distance

no code implementations23 Apr 2019 Zihao Wang, Datong Zhou, Yong Zhang, Hao Wu, Chenglong Bao

As a fundamental problem of natural language processing, it is important to measure the distance between different documents.

Semantic Similarity Semantic Textual Similarity

Persona-Aware Tips Generation

no code implementations6 Mar 2019 Piji Li, ZiHao Wang, Lidong Bing, Wai Lam

In order to exploit the persona information, we propose a framework based on adversarial variational auto-encoders (aVAE) for persona modeling from the historical tips and reviews of users and items.

Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing

no code implementations CVPR 2019 Xihui Liu, ZiHao Wang, Jing Shao, Xiaogang Wang, Hongsheng Li

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions.

Referring Expression

Automatically Segmenting the Left Atrium from Cardiac Images Using Successive 3D U-Nets and a Contour Loss

no code implementations6 Dec 2018 Shuman Jia, Antoine Despinasse, ZiHao Wang, Hervé Delingette, Xavier Pennec, Pierre Jaïs, Hubert Cochet, Maxime Sermesant

In this preliminary study, we propose automated, two-stage, three-dimensional U-Nets with convolutional neural network, for the challenging task of left atrial segmentation.

Semantic Segmentation

Responding E-commerce Product Questions via Exploiting QA Collections and Reviews

no code implementations COLING 2018 Qian Yu, Wai Lam, ZiHao Wang

Providing instant responses for product questions in E-commerce sites can significantly improve satisfaction of potential consumers.

Learning-To-Rank

Deep Recurrent Generative Decoder for Abstractive Text Summarization

1 code implementation EMNLP 2017 Piji Li, Wai Lam, Lidong Bing, ZiHao Wang

We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN).

Abstractive Text Summarization Variational Inference

Neural Rating Regression with Abstractive Tips Generation for Recommendation

no code implementations1 Aug 2017 Piji Li, ZiHao Wang, Zhaochun Ren, Lidong Bing, Wai Lam

In essence, writing some tips and giving a numerical rating are two facets of a user's product assessment action, expressing the user experience and feelings.

Compressive Holographic Video

no code implementations27 Oct 2016 Zihao Wang, Leonidas Spinoulas, Kuan He, Huaijin Chen, Lei Tian, Aggelos K. Katsaggelos, Oliver Cossairt

Compressive holography has been introduced as a method that allows 3D tomographic reconstruction at different depths from a single 2D image.

Super-Resolution

Competitive and Penalized Clustering Auto-encoder

no code implementations28 Aug 2015 Zihao Wang, Yiu-ming Cheung

In this paper, we present a novel regularization method based on a clustering algorithm which is able to classify the parameters into different groups.

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