Search Results for author: Zhi Li

Found 65 papers, 20 papers with code

UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings

no code implementations Findings (EMNLP) 2021 Zhi Li, Yuchen Zhai, Chengyu Wang, Minghui Qiu, Kailiang Li, Yin Zhang

Inspired by the fact that words with similar semantic can share a part of weights, we divide the embeddings of words into two parts: unique embedding and class embedding.

Language Modelling Semantic Similarity +2

VDIP-TGV: Blind Image Deconvolution via Variational Deep Image Prior Empowered by Total Generalized Variation

no code implementations30 Oct 2023 Tingting Wu, Zhiyan Du, Zhi Li, Feng-Lei Fan, Tieyong Zeng

However, we empirically find that VDIP struggles with processing image details and tends to generate suboptimal results when the blur kernel is large.

Deblurring Image Deconvolution

Spatial-Temporal Hypergraph Neural Network for Traffic Forecasting

no code implementations24 Oct 2023 Chengzhi Yao, Zhi Li, JunBo Wang

To tackle the above issues, we focus on the essence of traffic system and propose STHODE: Spatio-Temporal Hypergraph Neural Ordinary Differential Equation Network, which combines road network topology and traffic dynamics to capture high-order spatio-temporal dependencies in traffic data.

Efficient Real-time Path Planning with Self-evolving Particle Swarm Optimization in Dynamic Scenarios

1 code implementation20 Aug 2023 Jinghao Xin, Zhi Li, Yang Zhang, Ning li

Particle Swarm Optimization (PSO) has demonstrated efficacy in addressing static path planning problems.

OpenGCD: Assisting Open World Recognition with Generalized Category Discovery

1 code implementation14 Aug 2023 Fulin Gao, Weimin Zhong, Zhixing Cao, Xin Peng, Zhi Li

To bridge this gap, we propose OpenGCD that combines three key ideas to solve the above problems sequentially: (a) We score the origin of instances (unknown or specifically known) based on the uncertainty of the classifier's prediction; (b) For the first time, we introduce generalized category discovery (GCD) techniques in OWR to assist humans in grouping unlabeled data; (c) For the smooth execution of IL and GCD, we retain an equal number of informative exemplars for each class with diversity as the goal.

Continual Learning Incremental Learning +1

Rapid Flood Inundation Forecast Using Fourier Neural Operator

no code implementations29 Jul 2023 Alexander Y. Sun, Zhi Li, Wonhyun Lee, QiXing Huang, Bridget R. Scanlon, Clint Dawson

Flood inundation forecast provides critical information for emergency planning before and during flood events.

Depth Estimation Depth Prediction

Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms

1 code implementation14 Jul 2023 Qi Liu, Zheng Gong, Zhenya Huang, Chuanren Liu, HengShu Zhu, Zhi Li, Enhong Chen, Hui Xiong

Machine learning algorithms have become ubiquitous in a number of applications (e. g. image classification).

Image Classification

TL-nvSRAM-CIM: Ultra-High-Density Three-Level ReRAM-Assisted Computing-in-nvSRAM with DC-Power Free Restore and Ternary MAC Operations

no code implementations6 Jul 2023 Dengfeng Wang, Liukai Xu, Songyuan Liu, Zhi Li, Yiming Chen, Weifeng He, Xueqing Li, Yanan Su

Accommodating all the weights on-chip for large-scale NNs remains a great challenge for SRAM based computing-in-memory (SRAM-CIM) with limited on-chip capacity.

Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation

no code implementations14 Jun 2023 Likang Wu, Zhi Li, Hongke Zhao, Zhefeng Wang, Qi Liu, Baoxing Huai, Nicholas Jing Yuan, Enhong Chen

Zero-Shot Learning (ZSL), which aims at automatically recognizing unseen objects, is a promising learning paradigm to understand new real-world knowledge for machines continuously.

Knowledge Graphs World Knowledge +1

Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity

1 code implementation7 May 2023 Jinghao Xin, Jinwoo Kim, Zhi Li, Ning li

Meanwhile, the Sparrow simulator utilizes a 2D grid-based world, simplified kinematics, and conversion-free data flow to achieve a lightweight design.

Atari Games Robot Navigation

PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution

no code implementations24 Mar 2023 Hansheng Guo, Juncheng Li, Guangwei Gao, Zhi Li, Tieyong Zeng

Stereo image super-resolution aims to boost the performance of image super-resolution by exploiting the supplementary information provided by binocular systems.

Stereo Image Super-Resolution

Energy Management of Multi-mode Plug-in Hybrid Electric Vehicle using Multi-agent Deep Reinforcement Learning

no code implementations16 Mar 2023 Min Hua, Cetengfei Zhang, Fanggang Zhang, Zhi Li, Xiaoli Yu, Hongming Xu, Quan Zhou

The recently emerging multi-mode plug-in hybrid electric vehicle (PHEV) technology is one of the pathways making contributions to decarbonization, and its energy management requires multiple-input and multipleoutput (MIMO) control.

energy management Management

Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less

no code implementations ICCV 2023 Rizhao Cai, Yawen Cui, Zhi Li, Zitong Yu, Haoliang Li, Yongjian Hu, Alex Kot

To alleviate the forgetting of previous domains without using previous data, we propose the Proxy Prototype Contrastive Regularization (PPCR) to constrain the continual learning with previous domain knowledge from the proxy prototypes.

Continual Learning Domain Generalization +1

GUESR: A Global Unsupervised Data-Enhancement with Bucket-Cluster Sampling for Sequential Recommendation

no code implementations1 Mar 2023 Yongqiang Han, Likang Wu, Hao Wang, Guifeng Wang, Mengdi Zhang, Zhi Li, Defu Lian, Enhong Chen

Sequential Recommendation is a widely studied paradigm for learning users' dynamic interests from historical interactions for predicting the next potential item.

Contrastive Learning Sequential Recommendation

Electric Vehicle Sales Forecasting Model Considering Green Premium: A Chinese Market-based Perspective

no code implementations27 Feb 2023 Zhi Li, Hang Fan, Shuyan Dong

"Green Premiums" which means the difference in cost between emissions-emitting technology and zero-emissions or emissions-reducing technology is significant for those renewable energy technology to address the climate change challenge facing the world in this century.

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification

no code implementations20 Feb 2023 Mingyue Cheng, Qi Liu, Zhiding Liu, Zhi Li, Yucong Luo, Enhong Chen

Deep learning-based algorithms, e. g., convolutional networks, have significantly facilitated multivariate time series classification (MTSC) task.

Time Series Time Series Analysis +1

ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classification

no code implementations10 Feb 2023 Wenqiang He, Mingyue Cheng, Qi Liu, Zhi Li

Physiological signals are high-dimensional time series of great practical values in medical and healthcare applications.

Contrastive Learning Time Series +1

Virtual Try-On with Pose-Garment Keypoints Guided Inpainting

1 code implementation ICCV 2023 Zhi Li, Pengfei Wei, Xiang Yin, Zejun Ma, Alex C. Kot

In our method, human pose and garment keypoints are extracted from source images and constructed as graphs to predict the garment keypoints at the target pose.

Virtual Try-on

Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRF

no code implementations9 Nov 2022 Junzhe Jiang, Mingyue Cheng, Qi Liu, Zhi Li, Enhong Chen

Recognizing useful named entities plays a vital role in medical information processing, which helps drive the development of medical area research.

Medical Named Entity Recognition named-entity-recognition +3

Debiasing Graph Transfer Learning via Item Semantic Clustering for Cross-Domain Recommendations

1 code implementation7 Nov 2022 Zhi Li, Daichi Amagata, Yihong Zhang, Takahiro Hara, Shuichiro Haruta, Kei Yonekawa, Mori Kurokawa

To address this data sparsity problem, cross-domain recommender systems (CDRSs) exploit the data from an auxiliary source domain to facilitate the recommendation on the sparse target domain.

Clustering Recommendation Systems +1

One Person, One Model--Learning Compound Router for Sequential Recommendation

1 code implementation5 Nov 2022 Zhiding Liu, Mingyue Cheng, Zhi Li, Qi Liu, Enhong Chen

The core idea of CANet is to route the input user behaviors with a light-weighted router module.

Sequential Recommendation

Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning

no code implementations6 Sep 2022 Min Hua, Zhi Li, Quan Zhou

The study suggested that the MADRL with an independence ratio of 0. 2 is the best, and more than 2. 4% of energy can be saved over the conventional DRL framework.

energy management Management +2

MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes

1 code implementation17 Aug 2022 Zhi Li, Soshi Shimada, Bernt Schiele, Christian Theobalt, Vladislav Golyanik

3D human motion capture from monocular RGB images respecting interactions of a subject with complex and possibly deformable environments is a very challenging, ill-posed and under-explored problem.

3D Human Pose Estimation

Multi-modal Siamese Network for Entity Alignment

1 code implementation KDD 2022 Liyi Chen, Zhi Li, Tong Xu, Han Wu, Zhefeng Wang, Nicholas Jing Yuan, Enhong Chen

To deal with that problem, in this paper, we propose a novel Multi-modal Siamese Network for Entity Alignment (MSNEA) to align entities in different MMKGs, in which multi-modal knowledge could be comprehensively leveraged by the exploitation of inter-modal effect.

Ranked #7 on Multi-modal Entity Alignment on UMVM-oea-d-w-v1 (using extra training data)

Contrastive Learning Knowledge Graphs +2

Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cues

no code implementations10 Aug 2022 Zitong Yu, Rizhao Cai, Zhi Li, Wenhan Yang, Jingang Shi, Alex C. Kot

In this paper, we establish the first joint face spoofing and forgery detection benchmark using both visual appearance and physiological rPPG cues.

Benchmarking DeepFake Detection +3

HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance

no code implementations11 May 2022 Soshi Shimada, Vladislav Golyanik, Zhi Li, Patrick Pérez, Weipeng Xu, Christian Theobalt

Marker-less monocular 3D human motion capture (MoCap) with scene interactions is a challenging research topic relevant for extended reality, robotics and virtual avatar generation.

One-Class Knowledge Distillation for Face Presentation Attack Detection

1 code implementation8 May 2022 Zhi Li, Rizhao Cai, Haoliang Li, Kwok-Yan Lam, Yongjian Hu, Alex C. Kot

Under this framework, a teacher network is trained with source domain samples to provide discriminative feature representations for face PAD.

Face Presentation Attack Detection

Estimating the Resize Parameter in End-to-end Learned Image Compression

no code implementations26 Apr 2022 Li-Heng Chen, Christos G. Bampis, Zhi Li, Lukáš Krasula, Alan C. Bovik

By conducting extensive experimental tests on existing deep image compression models, we show results that our new resizing parameter estimation framework can provide Bj{\o}ntegaard-Delta rate (BD-rate) improvement of about 10% against leading perceptual quality engines.

Image Compression

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

no code implementations18 Apr 2022 Likang Wu, Hao Wang, Enhong Chen, Zhi Li, Hongke Zhao, Jianhui Ma

To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i. e., preference topics generation, preference shift modeling, and social influence activation.

ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning

no code implementations7 Feb 2022 Hao Wang, Zhi Li, Chunpeng Ge, Willy Susilo

To address the issue of privacy-preserving in collaborative learning, secure outsourced computation and federated learning are two typical methods.

BIG-bench Machine Learning Federated Learning +1

Asymmetric Modality Translation For Face Presentation Attack Detection

no code implementations18 Oct 2021 Zhi Li, Haoliang Li, Xin Luo, Yongjian Hu, Kwok-Yan Lam, Alex C. Kot

In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-modality scenarios.

Face Presentation Attack Detection Face Recognition +1

Learning Meta Pattern for Face Anti-Spoofing

1 code implementation13 Oct 2021 Rizhao Cai, Zhi Li, Renjie Wan, Haoliang Li, Yongjian Hu, Alex ChiChung Kot

To improve the generalization ability, recent hybrid methods have been explored to extract task-aware handcrafted features (e. g., Local Binary Pattern) as discriminative information for the input of DNNs.

Domain Generalization Face Anti-Spoofing +1

AutoChart: A Dataset for Chart-to-Text Generation Task

no code implementations RANLP 2021 Jiawen Zhu, Jinye Ran, Roy Ka-Wei Lee, Kenny Choo, Zhi Li

The analytical description of charts is an exciting and important research area with many applications in academia and industry.

Text Generation

KuiLeiXi: a Chinese Open-Ended Text Adventure Game

no code implementations ACL 2021 Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu

Equipped with GPT-2 and the latest GPT-3, AI Dungeon has been seen as a famous example of the powerful text generation capabilities of large-scale pre-trained language models, and a possibility for future games.

Story Generation

Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective

no code implementations27 May 2021 Likang Wu, Zhi Li, Hongke Zhao, Qi Liu, Enhong Chen

Usually, this prediction is always with great challenges to making a comprehensive understanding of both the start-up project and market environment.

Convolutional Block Design for Learned Fractional Downsampling

no code implementations20 May 2021 Li-Heng Chen, Christos G. Bampis, Zhi Li, Chao Chen, Alan C. Bovik

The layers of convolutional neural networks (CNNs) can be used to alter the resolution of their inputs, but the scaling factors are limited to integer values.

SSIM Video Compression

Color image segmentation based on a convex K-means approach

no code implementations17 Mar 2021 Tingting Wu, Xiaoyu Gu, Jinbo Shao, Ruoxuan Zhou, Zhi Li

The proposed variational method uses a combination of $l_1$ and $l_2$ regularizers to maintain edge information of objects in images while overcoming the staircase effect.

Image Segmentation Segmentation +1

Enhancing VMAF through New Feature Integration and Model Combination

no code implementations10 Mar 2021 Fan Zhang, Angeliki Katsenou, Christos Bampis, Lukas Krasula, Zhi Li, David Bull

VMAF is a machine learning based video quality assessment method, originally designed for streaming applications, which combines multiple quality metrics and video features through SVM regression.

regression Video Quality Assessment

Learning Skill Equivalencies Across Platform Taxonomies

1 code implementation10 Feb 2021 Zhi Li, Cheng Ren, Xianyou Li, Zachary A. Pardos

Assessment and reporting of skills is a central feature of many digital learning platforms.

Machine Translation Translation

Learning the Implicit Semantic Representation on Graph-Structured Data

1 code implementation16 Jan 2021 Likang Wu, Zhi Li, Hongke Zhao, Qi Liu, Jun Wang, Mengdi Zhang, Enhong Chen

Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while the implicit semantic associations behind highly complex interactions of graphs are largely unexploited.

Representation Learning

Origin of the Electronic Structure in Single-Layer FeSe/SrTiO3 Films

no code implementations16 Dec 2020 Defa Liu, Xianxin Wu, Fangsen Li, Yong Hu, Jianwei Huang, Yu Xu, Cong Li, Yunyi Zang, Junfeng He, Lin Zhao, Shaolong He, Chenjia Tang, Zhi Li, Lili Wang, Qingyan Wang, Guodong Liu, Zuyan Xu, Xu-Cun Ma, Qi-Kun Xue, Jiangping Hu, X. J. Zhou

These observations not only show the first direct evidence that the electronic structure of single-layer FeSe/SrTiO3 films originates from bulk FeSe through a combined effect of an electronic phase transition and an interfacial charge transfer, but also provide a quantitative basis for theoretical models in describing the electronic structure and understanding the superconducting mechanism in single-layer FeSe/SrTiO3 films.

Band Gap Superconductivity Strongly Correlated Electrons

Observation of Magnetic Droplets in Magnetic Tunnel Junctions

no code implementations10 Dec 2020 Kewen Shi, Wenlong Cai, Sheng Jiang, Daoqian Zhu, Kaihua Cao, Zongxia Guo, Jiaqi Wei, Ao Du, Zhi Li, Yan Huang, Jialiang Yin, Johan Akerman, Weisheng Zhao

Magnetic droplets, a class of highly non-linear magnetodynamical solitons, can be nucleated and stabilized in nanocontact spin-torque nano-oscillators where they greatly increase the microwave output power.

Applied Physics

Dynamic radiomics: a new methodology to extract quantitative time-related features from tomographic images

no code implementations1 Nov 2020 Fengying Che, Ruichuan Shi, Jian Wu, Haoran Li, Shuqin Li, Weixing Chen, Hao Zhang, Zhi Li, Xiaoyu Cui

The feature extraction methods of radiomics are mainly based on static tomographic images at a certain moment, while the occurrence and development of disease is a dynamic process that cannot be fully reflected by only static characteristics.

Strategy for Boosting Pair Comparison and Improving Quality Assessment Accuracy

no code implementations1 Oct 2020 Suiyi Ling, Jing Li, Anne Flore Perrin, Zhi Li, Lukáš Krasula, Patrick Le Callet

The development of rigorous quality assessment model relies on the collection of reliable subjective data, where the perceived quality of visual multimedia is rated by the human observers.

Sequence-to-Sequence Load Disaggregation Using Multi-Scale Residual Neural Network

no code implementations25 Sep 2020 Gan Zhou, Zhi Li, Meng Fu, Yanjun Feng, Xingyao Wang, Chengwei Huang

Secondly, we propose dilated convolution to curtail the excessive quantity of model parameters and obtain bigger receptive field, and multi-scale structure to learn mixed data features in a more targeted way.

Non-Intrusive Load Monitoring

MMEA: Entity Alignment for Multi-Modal Knowledge Graphs

1 code implementation20 Aug 2020 Liyi Chen, Zhi Li, Yijun Wang, Tong Xu, Zhefeng Wang, Enhong Chen

To that end, in this paper, we propose a novel solution called Multi-Modal Entity Alignment (MMEA) to address the problem of entity alignment in a multi-modal view.

Knowledge Graphs Multimodal Deep Learning +1

Perceptually Optimizing Deep Image Compression

no code implementations3 Jul 2020 Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin, Alan C. Bovik

Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties.

Image Compression

Learning the Compositional Visual Coherence for Complementary Recommendations

no code implementations8 Jun 2020 Zhi Li, Bo Wu, Qi Liu, Likang Wu, Hongke Zhao, Tao Mei

Towards this end, in this paper, we propose a novel Content Attentive Neural Network (CANN) to model the comprehensive compositional coherence on both global contents and semantic contents.

Can Machines “Learn” Halide Perovskite Crystal Formation without Accurate Physicochemical Features?

no code implementations26 May 2020 Ian M. Pendleton, Mary K. Caucci, Michael Tynes, Aaron Dharna, Mansoor Ani Najeeb Nellikkal, Zhi Li, Emory M. Chan, Alexander J. Norquist, and Joshua Schrier

To address limitations in previous work, we developed an improved description of the reactant concentrations in the experiments (validated against experimental observations) and performed experiments quantifying the excess volume of mixing of γ-butyrolactone/formic acid mixtures used in the perovskite syntheses.


Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model

no code implementations14 Dec 2019 Likang Wu, Zhi Li, Hongke Zhao, Zhen Pan, Qi Liu, Enhong Chen

In the crowdfunding market, the early fundraising performance of the project is a concerned issue for both creators and platforms.

ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

1 code implementation19 Oct 2019 Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin, Alan C. Bovik

By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as $31\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.

Image Compression

On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos

no code implementations ICCV 2019 Zhi Li, Xuan Wang, Fei Wang, Peilin Jiang

As illustrated in experiments, given only a small set of annotations, our method successfully makes the model to learn new poses from unlabelled monocular videos, promoting the accuracies of the baseline model by about 10%.

Weakly-supervised 3D Human Pose Estimation

Generalized Score Distribution

2 code implementations10 Sep 2019 Lucjan Janowski, Bogdan Ćmiel, Krzysztof Rusek, Jakub Nawała, Zhi Li

A class of discrete probability distributions contains distributions with limited support, i. e. possible argument values are limited to a set of numbers (typically consecutive).

Methodology Multimedia G.3

Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach

no code implementations30 May 2019 Min Hou, Le Wu, Enhong Chen, Zhi Li, Vincent W. Zheng, Qi Liu

When making cloth decisions, people usually show preferences for different semantic attributes (e. g., the clothes with v-neck collar).

Ranked #2 on Recommendation Systems on Amazon Fashion (using extra training data)

Recommendation Systems

Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors

no code implementations3 Aug 2018 Zhi Li, Hongke Zhao, Qi Liu, Zhenya Huang, Tao Mei, Enhong Chen

In this paper, we propose a novel Behavior-Intensive Neural Network (BINN) for next-item recommendation by incorporating both users' historical stable preferences and present consumption motivations.

Session-Based Recommendations

A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates

no code implementations25 Apr 2017 Zhi Li, Wei Shi, Ming Yan

This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms.

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