Search Results for author: Xi Zhang

Found 63 papers, 11 papers with code

FLLIC: Functionally Lossless Image Compression

no code implementations24 Jan 2024 Xi Zhang, Xiaolin Wu

Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the bit rate by about ten percent for natural color images.

Denoising Image Compression

A Survey of Text Watermarking in the Era of Large Language Models

no code implementations13 Dec 2023 Aiwei Liu, Leyi Pan, Yijian Lu, Jingjing Li, Xuming Hu, Xi Zhang, Lijie Wen, Irwin King, Hui Xiong, Philip S. Yu

Text watermarking algorithms play a crucial role in the copyright protection of textual content, yet their capabilities and application scenarios have been limited historically.

Dialogue Generation

Visual Commonsense based Heterogeneous Graph Contrastive Learning

no code implementations11 Nov 2023 Zongzhao Li, Xiangyu Zhu, Xi Zhang, Zhaoxiang Zhang, Zhen Lei

Specifically, our model contains two key components: the Commonsense-based Contrastive Learning and the Graph Relation Network.

Contrastive Learning Question Answering +4

Robust Ranking Explanations

no code implementations8 Jul 2023 Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie

Robust explanations of machine learning models are critical to establish human trust in the models.

LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression

no code implementations CVPR 2023 Xi Zhang, Xiaolin Wu

Recently, numerous end-to-end optimized image compression neural networks have been developed and proved themselves as leaders in rate-distortion performance.

Image Compression Quantization

HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces

no code implementations14 Feb 2023 Erich Liang, Kenan Deng, Xi Zhang, Chun-Kai Wang

Recent advances in neural implicit surfaces for multi-view 3D reconstruction primarily focus on improving large-scale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details.

3D Reconstruction Multi-View 3D Reconstruction +2

Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion

no code implementations13 Feb 2023 Xi Zhang, Xiaolin Wu

In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer.

Image Compression

Word-Graph2vec: An efficient word embedding approach on word co-occurrence graph using random walk technique

no code implementations11 Jan 2023 Wenting Li, Jiahong Xue, Xi Zhang, Huacan Chen, Zeyu Chen, Feijuan Huang, Yuanzhe Cai

Word embedding has become ubiquitous and is widely used in various natural language processing (NLP) tasks, such as web retrieval, web semantic analysis, and machine translation, and so on.

Information Retrieval Machine Translation +1

VQACL: A Novel Visual Question Answering Continual Learning Setting

1 code implementation CVPR 2023 Xi Zhang, Feifei Zhang, Changsheng Xu

Research on continual learning has recently led to a variety of work in unimodal community, however little attention has been paid to multimodal tasks like visual question answering (VQA).

Continual Learning Question Answering +2

Provable Robust Saliency-based Explanations

no code implementations28 Dec 2022 Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie

Robust explanations of machine learning models are critical to establishing human trust in the models.

Unsupervised Scene Sketch to Photo Synthesis

1 code implementation6 Sep 2022 Jiayun Wang, Sangryul Jeon, Stella X. Yu, Xi Zhang, Himanshu Arora, Yu Lou

Taking this advantage, we synthesize a photo-realistic image by combining the structure of a sketch and the visual style of a reference photo.

MFAN: Multi-modal Feature-enhanced Attention Networks for Rumor Detection

1 code implementation 2022 2022 Jiaqi Zheng, Xi Zhang, Sanchuan Guo, Quan Wang, Wenyu Zang, Yongdong Zhang

Rumor spreaders are increasingly taking advantage of multimedia content to attract and mislead news consumers on social media.

Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users

no code implementations24 Apr 2022 Zheng Zhang, Yingsheng Ji, Jiachen Shen, Xi Zhang, Guangwen Yang

Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications.

Feature Engineering Implicit Relations

Structured Graph Variational Autoencoders for Indoor Furniture layout Generation

no code implementations11 Apr 2022 Aditya Chattopadhyay, Xi Zhang, David Paul Wipf, Himanshu Arora, Rene Vidal

The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph.

Values of Coordinated Residential Space Heating in Demand Response Provision

no code implementations23 Mar 2022 Zihang Dong, Xi Zhang, Goran Strbac

Demand-side response from space heating in residential buildings can potentially provide a huge amount of flexibility for the power system, particularly with deep electrification of the heat sector.

Deep Decoding of $\ell_\infty$-coded Light Field Images

no code implementations24 Jan 2022 Muhammad Umair Mukati, Xi Zhang, Xiaolin Wu, Søren Forchhammer

To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations.

Image Compression

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection

no code implementations15 Jan 2022 Yuefei Lyu, Xiaoyu Yang, Jiaxin Liu, Philip S. Yu, Sihong Xie, Xi Zhang

To discover subtle vulnerabilities, we design a powerful attacking algorithm to camouflage rumors in social networks based on reinforcement learning that can interact with and attack any black-box detectors.

reinforcement-learning Reinforcement Learning (RL)

Multi-objective Explanations of GNN Predictions

no code implementations29 Nov 2021 Yifei Liu, Chao Chen, Yazheng Liu, Xi Zhang, Sihong Xie

We design a user study to investigate such joint effects and use the findings to design a multi-objective optimization (MOO) algorithm to find Pareto optimal explanations that are well-balanced in simulatability and counterfactual.

counterfactual Decision Making +1

Explaining GNN over Evolving Graphs using Information Flow

no code implementations19 Nov 2021 Yazheng Liu, Xi Zhang, Sihong Xie

We define the problem of explaining evolving GNN predictions and propose an axiomatic attribution method to uniquely decompose the change in a prediction to paths on computation graphs.

Knowledge Graphs

RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View

no code implementations1 Oct 2021 Xi Zhang, Chun-Kai Wang, Kenan Deng, Tomas Yago-Vicente, Himanshu Arora

In addition to using learnt robust features, our approach learns an additional ranking function to estimate the final layout instead of using optimization.

Learning-To-Rank

Self-learn to Explain Siamese Networks Robustly

no code implementations15 Sep 2021 Chao Chen, Yifan Shen, Guixiang Ma, Xiangnan Kong, Srinivas Rangarajan, Xi Zhang, Sihong Xie

Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.

Face Recognition Fairness +1

Multi-modality Deep Restoration of Extremely Compressed Face Videos

no code implementations5 Jul 2021 Xi Zhang, Xiaolin Wu

Arguably the most common and salient object in daily video communications is the talking head, as encountered in social media, virtual classrooms, teleconferences, news broadcasting, talk shows, etc.

Quantization

THP: Topological Hawkes Processes for Learning Causal Structure on Event Sequences

no code implementations23 May 2021 Ruichu Cai, Siyu Wu, Jie Qiao, Zhifeng Hao, Keli Zhang, Xi Zhang

We further propose a causal structure learning method on THP in a likelihood framework.

An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks

1 code implementation7 May 2021 Keli Zhang, Marcus Kalander, Min Zhou, Xi Zhang, Junjian Ye

Alarm root cause analysis is a significant component in the day-to-day telecommunication network maintenance, and it is critical for efficient and accurate fault localization and failure recovery.

Causal Inference Fault localization +2

Probing quasi-long-range ordering by magnetostriction in monolayer CoPS3

no code implementations4 Jan 2021 Qiye Liu, Le Wang, Ying Fu, Xi Zhang, Lianglong Huang, Huimin Su, Junhao Lin, Xiaobin Chen, Dapeng Yu, Xiaodong Cui, Jia-Wei Mei, Jun-Feng Dai

Mermin-Wagner-Coleman theorem predicts no long-range magnetic order at finite temperature in the two-dimensional (2D) isotropic systems, but a quasi-long-range order with a divergent correlation length at the Kosterlitz-Thouless (KT) transition for planar magnets.

Mesoscale and Nanoscale Physics

Haze Formation on Triton

no code implementations22 Dec 2020 Kazumasa Ohno, Xi Zhang, Ryo Tazaki, Satoshi Okuzumi

We simulated the formation of sphere and aggregate hazes with and without condensation of the C$_2$H$_4$ ice.

Earth and Planetary Astrophysics

On Numerosity of Deep Neural Networks

no code implementations NeurIPS 2020 Xi Zhang, Xiaolin Wu

With the above critique we ask the question what if a deep convolutional neural network is carefully trained for numerosity?

Object Recognition

Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos

no code implementations2 Aug 2020 Yanhui Guo, Xi Zhang, Xiaolin Wu

We propose a novel deep multi-modality neural network for restoring very low bit rate videos of talking heads.

Quantization Video Compression +1

Local Causal Structure Learning and its Discovery Between Type 2 Diabetes and Bone Mineral Density

no code implementations27 Jun 2020 Wei Wang, Gangqiang Hu, Bo Yuan, Shandong Ye, Chao Chen, YaYun Cui, Xi Zhang, Liting Qian

To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.

DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads

no code implementations CVPR 2020 Xi Zhang, Xiaolin Wu, Xinliang Zhai, Xianye Ben, Chengjie Tu

Close-up talking heads are among the most common and salient object in video contents, such as face-to-face conversations in social media, teleconferences, news broadcasting, talk shows, etc.

Video Compression Video Reconstruction

Rigorous Explanation of Inference on Probabilistic Graphical Models

no code implementations21 Apr 2020 Yifei Liu, Chao Chen, Xi Zhang, Sihong Xie

There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models.

Attribute Decision Making

Ultra High Fidelity Image Compression with $\ell_\infty$-constrained Encoding and Deep Decoding

no code implementations10 Feb 2020 Xi Zhang, Xiaolin Wu

We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-constrained decoding method.

Image Compression

MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing

no code implementations7 Feb 2020 Yu Zhang, Tao Gu, Xi Zhang

Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications.

Federated Learning Multi-Goal Reinforcement Learning

Scalable Explanation of Inferences on Large Graphs

no code implementations13 Aug 2019 Chao Chen, Yifei Liu, Xi Zhang, Sihong Xie

Probabilistic inferences distill knowledge from graphs to aid human make important decisions.

Challenge of Spatial Cognition for Deep Learning

no code implementations30 Jul 2019 Xi Zhang, Xiaolin Wu, Jun Du

Given the success of the deep convolutional neural networks (DCNNs) in applications of visual recognition and classification, it would be tantalizing to test if DCNNs can also learn spatial concepts, such as straightness, convexity, left/right, front/back, relative size, aspect ratio, polygons, etc., from varied visual examples of these concepts that are simple and yet vital for spatial reasoning.

Test

Nonlinear Prediction of Multidimensional Signals via Deep Regression with Applications to Image Coding

no code implementations30 Oct 2018 Xi Zhang, Xiaolin Wu

Deep convolutional neural networks (DCNN) have enjoyed great successes in many signal processing applications because they can learn complex, non-linear causal relationships from input to output.

regression

Enhancing Stock Market Prediction with Extended Coupled Hidden Markov Model over Multi-Sourced Data

no code implementations2 Sep 2018 Xi Zhang, Yixuan Li, Senzhang Wang, Binxing Fang, Philip S. Yu

In this work, we study how to explore multiple data sources to improve the performance of the stock prediction.

Stock Prediction

Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval

no code implementations ECCV 2018 Xi Zhang, Hanjiang Lai , Jiashi Feng

The proposed new deep adversarial network consists of three building blocks: 1) the feature learning module to obtain the feature representations; 2) the attention module to generate an attention mask, which is used to divide the feature representations into the attended and unattended feature representations; and 3) the hashing module to learn hash functions that preserve the similarities between different modalities.

Cross-Modal Retrieval Retrieval

Multi-region segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks

no code implementations28 May 2018 Jose Dolz, Xiaopan Xu, Jerome Rony, Jing Yuan, Yang Liu, Eric Granger, Christian Desrosiers, Xi Zhang, Ismail Ben Ayed, Hongbing Lu

Precise segmentation of bladder walls and tumor regions is an essential step towards non-invasive identification of tumor stage and grade, which is critical for treatment decision and prognosis of patients with bladder cancer (BC).

Segmentation

A Tensor-Based Sub-Mode Coordinate Algorithm for Stock Prediction

no code implementations21 May 2018 Jieyun Huang, Yunjia Zhang, Jialai Zhang, Xi Zhang

The results demonstrate the improvement on the prediction accuracy and the effectiveness of the proposed model.

Stock Prediction Tensor Decomposition

Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask

no code implementations9 May 2018 Xi Zhang, Di Ma, Xu Ouyang, Shanshan Jiang, Lin Gan, Gady Agam

We show that by using masks the motion estimate results in a quadratic function of input features in the output layer.

Motion Estimation Optical Flow Estimation

Cognitive Deficit of Deep Learning in Numerosity

no code implementations9 Feb 2018 Xiaolin Wu, Xi Zhang, Xiao Shu

Subitizing, or the sense of small natural numbers, is an innate cognitive function of humans and primates; it responds to visual stimuli prior to the development of any symbolic skills, language or arithmetic.

Test

Lecture video indexing using boosted margin maximizing neural networks

no code implementations2 Dec 2017 Di Ma, Xi Zhang, Xu Ouyang, Gady Agam

This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system.

HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval

no code implementations26 Nov 2017 Xi Zhang, Siyu Zhou, Jiashi Feng, Hanjiang Lai, Bo Li, Yan Pan, Jian Yin, Shuicheng Yan

The proposed new adversarial network, HashGAN, consists of three building blocks: 1) the feature learning module to obtain feature representations, 2) the generative attention module to generate an attention mask, which is used to obtain the attended (foreground) and the unattended (background) feature representations, 3) the discriminative hash coding module to learn hash functions that preserve the similarities between different modalities.

Cross-Modal Retrieval Retrieval

Aicyber's System for NLPCC 2017 Shared Task 2: Voting of Baselines

no code implementations15 Nov 2017 Du Steven, Xi Zhang

This paper presents Aicyber's system for NLPCC 2017 shared task 2.

Task 2

Patient Subtyping via Time-Aware LSTM Networks

1 code implementation KDD '17 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2017 Inci M. Baytas, Cao Xiao, Xi Zhang, Fei Wang, Anil K. Jain, Jiayu Zhou

We propose a patient subtyping model that leverages the proposed T-LSTM in an auto-encoder to learn a powerful single representation for sequential records of patients, which are then used to cluster patients into clinical subtypes.

Multivariate Time Series Forecasting

Responses to Critiques on Machine Learning of Criminality Perceptions (Addendum of arXiv:1611.04135)

no code implementations13 Nov 2016 Xiaolin Wu, Xi Zhang

In November 2016 we submitted to arXiv our paper "Automated Inference on Criminality Using Face Images".

BIG-bench Machine Learning

CGMOS: Certainty Guided Minority OverSampling

1 code implementation21 Jul 2016 Xi Zhang, Di Ma, Lin Gan, Shanshan Jiang, Gady Agam

In this paper we propose a novel extension to the SMOTE algorithm with a theoretical guarantee for improved classification performance.

Classification General Classification

Modular Decomposition and Analysis of Registration based Trackers

no code implementations3 Mar 2016 Abhineet Singh, Ankush Roy, Xi Zhang, Martin Jagersand

We show how existing trackers can be broken down using the suggested methodology and compare the performance of the default configuration chosen by the authors against other possible combinations to demonstrate the new insights that can be gained by such an approach.

Test

Learning from Synthetic Data Using a Stacked Multichannel Autoencoder

no code implementations17 Sep 2015 Xi Zhang, Yanwei Fu, Shanshan Jiang, Leonid Sigal, Gady Agam

In this paper, we investigate and formalize a general framework-Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently.

Sketch Recognition

Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

no code implementations11 Mar 2015 Xi Zhang, Yanwei Fu, Andi Zang, Leonid Sigal, Gady Agam

Experimental results on two datasets validate the efficiency of our MCAE model and our methodology of generating synthetic data.

General Classification

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