Search Results for author: Lin Li

Found 125 papers, 33 papers with code

Chinese Long and Short Form Choice Exploiting Neural Network Language Modeling Approaches

no code implementations CCL 2020 Lin Li, Kees Van Deemter, Denis Paperno

This paper presents our work in long and short form choice, a significant question of lexical choice, which plays an important role in many Natural Language Understanding tasks.

Language Modelling Natural Language Understanding

标签先验知识增强的方面类别情感分析方法研究(Aspect-Category based Sentiment Analysis Enhanced by Label Prior Knowledge)

no code implementations CCL 2022 Renwei Wu, Lin Li, Zheng He, Jingling Yuan

“当前, 基于方面类别的情感分析研究旨在将方面类别检测和面向类别的情感分类两个任务协同进行。然而, 现有研究未能有效关注情感数据集中存在的噪声标签, 影响了情感分析的质量。基于此, 本文提出一种标签先验知识增强的方面类别情感分析方法(AP-LPK)。首先本文为面向类别的情感分类构建了自回归提示训练方式, 可以激发预训练语言模型的潜力。同时该方式通过自回归生成标签词, 以期获得比非自回归更好的语义一致性。其次, 每个类别的标签分布作为标签先验知识引入, 并通过伯努利分布对其进行进一步精炼, 以用于减轻噪声标签的干扰。然后, AP-LPK将上述两个步骤分别得到的情感类别分布进行融合, 以获得最终的情感类别预测概率。最后, 本文提出的AP-LPK方法在五个数据集上进行评估, 包括SemEval 2015和2016的四个基准数据集和AI Challenger 2018的餐厅领域大规模数据集。实验结果表明, 本文提出的方法在F1指标上优于现有方法。”

Sentiment Analysis

Gradations of Error Severity in Automatic Image Descriptions

no code implementations INLG (ACL) 2020 Emiel van Miltenburg, Wei-Ting Lu, Emiel Krahmer, Albert Gatt, Guanyi Chen, Lin Li, Kees Van Deemter

Because our manipulated descriptions form minimal pairs with the reference descriptions, we are able to assess the impact of different kinds of errors on the perceived quality of the descriptions.

Enhancing Sign Language Teaching: A Mixed Reality Approach for Immersive Learning and Multi-Dimensional Feedback

no code implementations16 Apr 2024 Hongli Wen, Yang Xu, Lin Li, Xudong Ru, Xingce Wang, Zhongke Wu

Furthermore, we use mixed reality technology to construct a scenario-based 3D sign language classroom and explore the user experience of scenario teaching.

Mixed Reality

On Unified Prompt Tuning for Request Quality Assurance in Public Code Review

no code implementations11 Apr 2024 Xinyu Chen, Lin Li, Rui Zhang, Peng Liang

Public Code Review (PCR) can be implemented through a Software Question Answering (SQA) community, which facilitates high knowledge dissemination.

Language Modelling Question Answering

MealRec$^+$: A Meal Recommendation Dataset with Meal-Course Affiliation for Personalization and Healthiness

1 code implementation8 Apr 2024 Ming Li, Lin Li, Xiaohui Tao, Jimmy Xiangji Huang

Due to constraints related to user health privacy and meal scenario characteristics, the collection of data that includes both meal-course affiliation and two levels of interactions is impeded.

Federated Distillation: A Survey

no code implementations2 Apr 2024 Lin Li, Jianping Gou, Baosheng Yu, Lan Du, Zhang Yiand Dacheng Tao

Federated Learning (FL) seeks to train a model collaboratively without sharing private training data from individual clients.

Federated Learning Knowledge Distillation +1

ContourDiff: Unpaired Image Translation with Contour-Guided Diffusion Models

no code implementations16 Mar 2024 YuWen Chen, Nicholas Konz, Hanxue Gu, Haoyu Dong, Yaqian Chen, Lin Li, Jisoo Lee, Maciej A. Mazurowski

We evaluate our method by training a segmentation model on images translated from CT to MRI with their original CT masks and testing its performance on real MRIs.

Anatomy Translation

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

1 code implementation4 Mar 2024 Lin Li, Haoyan Guan, Jianing Qiu, Michael Spratling

This work studies the adversarial robustness of VLMs from the novel perspective of the text prompt instead of the extensively studied model weights (frozen in this work).

Adversarial Attack Adversarial Robustness

Primary and Secondary Factor Consistency as Domain Knowledge to Guide Happiness Computing in Online Assessment

no code implementations17 Feb 2024 Xiaohua Wu, Lin Li, Xiaohui Tao, Frank Xing, Jingling Yuan

We achieve this through: (1) proving that multiple prediction models with additive factor attributions will have the desirable property of primary and secondary relations consistency, and (2) showing that factor relations with quantity can be represented as an importance distribution for encoding domain knowledge.

Towards Causal Classification: A Comprehensive Study on Graph Neural Networks

no code implementations27 Jan 2024 Simi Job, Xiaohui Tao, Taotao Cai, Lin Li, Haoran Xie, Jianming Yong

The exploration of Graph Neural Networks (GNNs) for processing graph-structured data has expanded, particularly their potential for causal analysis due to their universal approximation capabilities.

Graph Classification

Persona-centric Metamorphic Relation guided Robustness Evaluation for Multi-turn Dialogue Modelling

no code implementations23 Jan 2024 Yanbing Chen, Lin Li, Xiaohui Tao, Dong Zhou

For that reason, this work evaluates several widely used training paradigms including learning from scratch, pretrain + fine-tune and prompt learning in personalized dialogue retrieval to know if they are more robust or if they have the same flaws as their predecessor.

Reading Comprehension Relation +1

MM-TTS: Multi-modal Prompt based Style Transfer for Expressive Text-to-Speech Synthesis

no code implementations17 Dec 2023 Wenhao Guan, Yishuang Li, Tao Li, Hukai Huang, Feng Wang, Jiayan Lin, Lingyan Huang, Lin Li, Qingyang Hong

The challenges of modeling such a multi-modal style controllable TTS mainly lie in two aspects:1)aligning the multi-modal information into a unified style space to enable the input of arbitrary modality as the style prompt in a single system, and 2)efficiently transferring the unified style representation into the given text content, thereby empowering the ability to generate prompt style-related voice.

Speech Synthesis Style Transfer +1

Higher-Order Equivariant Neural Networks for Charge Density Prediction in Materials

1 code implementation8 Dec 2023 Teddy Koker, Keegan Quigley, Eric Taw, Kevin Tibbetts, Lin Li

The calculation of electron density distribution using density functional theory (DFT) in materials and molecules is central to the study of their quantum and macro-scale properties, yet accurate and efficient calculation remains a long-standing challenge.

Property Prediction

Compositional Zero-shot Learning via Progressive Language-based Observations

no code implementations23 Nov 2023 Lin Li, Guikun Chen, Jun Xiao, Long Chen

Compositional zero-shot learning aims to recognize unseen state-object compositions by leveraging known primitives (state and object) during training.

Compositional Zero-Shot Learning

Interpretable Geoscience Artificial Intelligence (XGeoS-AI): Application to Demystify Image Recognition

no code implementations8 Nov 2023 Jin-Jian Xu, Hao Zhang, Chao-Sheng Tang, Lin Li, Bin Shi

Experimental results demonstrate that the effectiveness, versatility, and heuristics of the proposed framework have great potential in solving geoscience image recognition problems.

Computed Tomography (CT)

Cross-domain Robust Deepfake Bias Expansion Network for Face Forgery Detection

no code implementations8 Oct 2023 Weihua Liu, Lin Li, Chaochao Lin, Said Boumaraf

In addition, to further heighten the amplification of forged clues, BENet incorporates a Latent-Space Attention (LSA) module.

Face Recognition Face Swapping

LEGO-Prover: Neural Theorem Proving with Growing Libraries

1 code implementation1 Oct 2023 Haiming Wang, Huajian Xin, Chuanyang Zheng, Lin Li, Zhengying Liu, Qingxing Cao, Yinya Huang, Jing Xiong, Han Shi, Enze Xie, Jian Yin, Zhenguo Li, Heng Liao, Xiaodan Liang

Our ablation study indicates that these newly added skills are indeed helpful for proving theorems, resulting in an improvement from a success rate of 47. 1% to 50. 4%.

 Ranked #1 on Automated Theorem Proving on miniF2F-test (Pass@100 metric)

Automated Theorem Proving

Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion

no code implementations20 Sep 2023 Thanveer Shaik, Xiaohui Tao, Lin Li, Niall Higgins, Raj Gururajan, Xujuan Zhou, Jianming Yong

In our study, we propose a novel Clustered FedStack framework based on the previously published Stacked Federated Learning (FedStack) framework.

Clustering Federated Learning +1

PDRL: Multi-Agent based Reinforcement Learning for Predictive Monitoring

no code implementations19 Sep 2023 Thanveer Shaik, Xiaohui Tao, Lin Li, Haoran Xie, U R Acharya, Raj Gururajan, Xujuan Zhou

The PDRL framework is able to learn the future states of the traffic and weather forecasting and the cumulative rewards are gradually increasing over each episode.

reinforcement-learning Time Series +3

Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence

no code implementations18 Sep 2023 Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Jianming Yong, Yuefeng Li

In this study, we propose a novel approach for predicting time-series data using GNN and monitoring with Reinforcement Learning (RL).

Bayesian Optimisation reinforcement-learning +5

When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System

no code implementations13 Sep 2023 Hao Zhang, Jin-Jian Xu, Hong-Wei Cui, Lin Li, Yaowen Yang, Chao-Sheng Tang, Niklas Boers

Critically, the scalability and generalizability of GFMs empower them to address a wide array of prediction, simulation, and decision tasks related to the intricate interactions among Earth system components.

FIMO: A Challenge Formal Dataset for Automated Theorem Proving

1 code implementation8 Sep 2023 Chengwu Liu, Jianhao Shen, Huajian Xin, Zhengying Liu, Ye Yuan, Haiming Wang, Wei Ju, Chuanyang Zheng, Yichun Yin, Lin Li, Ming Zhang, Qun Liu

We present FIMO, an innovative dataset comprising formal mathematical problem statements sourced from the International Mathematical Olympiad (IMO) Shortlisted Problems.

Automated Theorem Proving

Compositional Feature Augmentation for Unbiased Scene Graph Generation

1 code implementation ICCV 2023 Lin Li, Guikun Chen, Jun Xiao, Yi Yang, Chunping Wang, Long Chen

Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation triplet, respectively.

Graph Generation Relation +1

RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent

no code implementations6 Jul 2023 Yijie Deng, Lei Han, Tianpeng Lin, Lin Li, Jinzhi Zhang, Lu Fang

Based on this insight, we introduce EffLiFe, a novel light field optimization method, which leverages the proposed Hierarchical Sparse Gradient Descent (HSGD) to produce high-quality light fields from sparse view images in real time.

Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization

no code implementations26 Jun 2023 Jie Wang, Zhicong Chen, Haodong Zhou, Lin Li, Qingyang Hong

The CDGCN-based clustering method consists of graph generation, sub-graph detection, and Graph-based Overlapped Speech Detection (Graph-OSD).

Clustering Community Detection +3

A Survey of Multimodal Information Fusion for Smart Healthcare: Mapping the Journey from Data to Wisdom

no code implementations21 Jun 2023 Thanveer Shaik, Xiaohui Tao, Lin Li, Haoran Xie, Juan D. Velásquez

The components of the comprehensive survey presented in this paper form the foundation for more successful implementation of multimodal fusion in smart healthcare.

feature selection

AROID: Improving Adversarial Robustness through Online Instance-wise Data Augmentation

no code implementations12 Jun 2023 Lin Li, Jianing Qiu, Michael Spratling

This allows our method to efficiently explore a large search space for a more effective DA policy and evolve the policy as training progresses.

Adversarial Robustness Data Augmentation

CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learning

no code implementations1 Jun 2023 Jianhua Wang, Xiaolin Chang, Jelena Mišić, Vojislav B. Mišić, Lin Li, Yingying Yao

Federated Learning (FL), a privacy-oriented distributed ML paradigm, is being gaining great interest in Internet of Things because of its capability to protect participants data privacy.

Federated Learning Privacy Preserving

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

1 code implementation NeurIPS 2023 Lin Li, Jun Xiao, Guikun Chen, Jian Shao, Yueting Zhuang, Long Chen

To dynamically fuse different cues, we further introduce a chain-of-thought method that prompts LLMs to generate reasonable weights for different visual cues.


Machine-learning-accelerated simulations to enable automatic surface reconstruction

1 code implementation12 May 2023 Xiaochen Du, James K. Damewood, Jaclyn R. Lunger, Reisel Millan, Bilge Yildiz, Lin Li, Rafael Gómez-Bombarelli

Here, we present a bi-faceted computational loop to predict surface phase diagrams of multi-component materials that accelerates both the energy scoring and statistical sampling methods.

Active Learning Surface Reconstruction

Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy

no code implementations10 May 2023 Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Xiaofeng Zhu, Qing Li

Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models.

Fairness Machine Unlearning +1

Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing

1 code implementation24 Mar 2023 Lin Li, Michael Spratling

We find that during training an overall reduction of adversarial loss is achieved by sacrificing a considerable proportion of training samples to be more vulnerable to adversarial attack, which results in an uneven distribution of adversarial vulnerability among data.

Adversarial Attack Adversarial Robustness +1

Large AI Models in Health Informatics: Applications, Challenges, and the Future

1 code implementation21 Mar 2023 Jianing Qiu, Lin Li, Jiankai Sun, Jiachuan Peng, Peilun Shi, Ruiyang Zhang, Yinzhao Dong, Kyle Lam, Frank P. -W. Lo, Bo Xiao, Wu Yuan, Ningli Wang, Dong Xu, Benny Lo

Large AI models, or foundation models, are models recently emerging with massive scales both parameter-wise and data-wise, the magnitudes of which can reach beyond billions.

Decision Making Drug Discovery +1

A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection

1 code implementation7 Mar 2023 Haocheng Ju, Haimiao Zhang, Lin Li, Xiao Li, Bin Dong

Joint channel estimation and signal detection (JCESD) in wireless communication systems is a crucial and challenging task, especially since it inherently poses a nonlinear inverse problem.

Rolling Shutter Correction

A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation

1 code implementation28 Feb 2023 Lin Li, Wendong Ding, Yongkun Wen, Yufei Liang, Yong liu, Guowei Wan

For overlap detection, a cross-attention module is applied for interacting contextual information of input point clouds, followed by a classification head to estimate the overlapping region.

Point Cloud Registration

Data Augmentation Alone Can Improve Adversarial Training

1 code implementation24 Jan 2023 Lin Li, Michael Spratling

Data augmentation, which is effective at preventing overfitting in standard training, has been observed by many previous works to be ineffective in mitigating overfitting in adversarial training.

Data Augmentation

Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization

1 code implementation9 Dec 2022 Lin Li, Michael Spratling

Adversarial training is widely used to improve the robustness of deep neural networks to adversarial attack.

Adversarial Attack

Graph Contrastive Learning for Materials

no code implementations24 Nov 2022 Teddy Koker, Keegan Quigley, Will Spaeth, Nathan C. Frey, Lin Li

By leveraging a series of material-specific transformations, we introduce CrystalCLR, a framework for constrastive learning of representations with crystal graph neural networks.

Contrastive Learning

Towards A Unified Conformer Structure: from ASR to ASV Task

1 code implementation14 Nov 2022 Dexin Liao, Tao Jiang, Feng Wang, Lin Li, Qingyang Hong

Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field of Automatic Speech Recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

1 code implementation22 Jul 2022 Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta, Guchun Zhang, Yinpeng Guo, Zhongqi Li, Qi Zhang, Meng Xiao, Bo Shen, Lin Li, Hao Yu, Li Yan, Pingyi Zhou, Xin Wang, Yuchi Ma, Ignacio Iacobacci, Yasheng Wang, Guangtai Liang, Jiansheng Wei, Xin Jiang, Qianxiang Wang, Qun Liu

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.

Code Generation Decoder +3

Learning to Prove Trigonometric Identities

no code implementations14 Jul 2022 Zhou Liu, YuJun Li, Zhengying Liu, Lin Li, Zhenguo Li

We define the normalized form of trigonometric identities, design a set of rules for the proof and put forward a method which can generate theoretically infinite trigonometric identities.

Automated Theorem Proving Imitation Learning

Trichomonas Vaginalis Segmentation in Microscope Images

no code implementations3 Jul 2022 Lin Li, Jingyi Liu, Shuo Wang, Xunkun Wang, Tian-Zhu Xiang

Trichomoniasis is a common infectious disease with high incidence caused by the parasite Trichomonas vaginalis, increasing the risk of getting HIV in humans if left untreated.

Object object-detection +2

Towards Real-Time Visual Tracking with Graded Color-names Features

no code implementations17 Jun 2022 Lin Li, Guoli Wang, Xuemei Guo

MeanShift algorithm has been widely used in tracking tasks because of its simplicity and efficiency.

Real-Time Visual Tracking

The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

1 code implementation CVPR 2022 Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, Jun Xiao

Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples.

Graph Generation Out-of-Distribution Detection +2

Deep Representation Decomposition for Rate-Invariant Speaker Verification

no code implementations28 May 2022 Fuchuan Tong, Siqi Zheng, Haodong Zhou, Xingjia Xie, Qingyang Hong, Lin Li

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability.

Speaker Verification

MealRec: A Meal Recommendation Dataset

1 code implementation24 May 2022 Ming Li, Lin Li, Qing Xie, Jingling Yuan, Xiaohui Tao

A publicly available dataset specialising in meal recommendation research for the research community is in urgent demand.

Recommendation Systems

Improving Cross-lingual Speech Synthesis with Triplet Training Scheme

no code implementations22 Feb 2022 Jianhao Ye, Hongbin Zhou, Zhiba Su, Wendi He, Kaimeng Ren, Lin Li, Heng Lu

Recent advances in cross-lingual text-to-speech (TTS) made it possible to synthesize speech in a language foreign to a monolingual speaker.

Speech Synthesis

What is Next when Sequential Prediction Meets Implicitly Hard Interaction?

no code implementations14 Feb 2022 Kaixi Hu, Lin Li, Qing Xie, Jianquan Liu, Xiaohui Tao

The experiences in the form of the unlikelihood of correct responses are drawn from each other by MED, which provides mutual exclusivity knowledge to figure out implicitly hard interactions.

Dual Space Graph Contrastive Learning

no code implementations19 Jan 2022 Haoran Yang, Hongxu Chen, Shirui Pan, Lin Li, Philip S. Yu, Guandong Xu

In addition, we conduct extensive experiments to analyze the impact of different graph encoders on DSGC, giving insights about how to better leverage the advantages of contrastive learning between different spaces.

Contrastive Learning Graph Learning +1

Scalable Geometric Deep Learning on Molecular Graphs

1 code implementation NeurIPS Workshop AI4Scien 2021 Nathan C. Frey, Siddharth Samsi, Joseph McDonald, Lin Li, Connor W. Coley, Vijay Gadepally

Deep learning in molecular and materials sciences is limited by the lack of integration between applied science, artificial intelligence, and high-performance computing.

Adder Attention for Vision Transformer

4 code implementations NeurIPS 2021 Han Shu, Jiahao Wang, Hanting Chen, Lin Li, Yujiu Yang, Yunhe Wang

With the new operation, vision transformers constructed using additions can also provide powerful feature representations.

Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation

no code implementations24 Nov 2021 Yicong Li, Hongxu Chen, Yile Li, Lin Li, Philip S. Yu, Guandong Xu

Recent advances in path-based explainable recommendation systems have attracted increasing attention thanks to the rich information provided by knowledge graphs.

Explainable Recommendation Knowledge Graphs +3

Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering

1 code implementation22 Oct 2021 Zhongwei Xie, Ling Liu, Yanzhao Wu, Luo Zhong, Lin Li

This paper introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint embedding model.

Cross-Modal Retrieval Feature Engineering +1

Visual-aware Attention Dual-stream Decoder for Video Captioning

no code implementations16 Oct 2021 Zhixin Sun, Xian Zhong, Shuqin Chen, Lin Li, Luo Zhong

Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence.

Decoder Video Captioning +1

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

no code implementations15 Oct 2021 Yiming Cui, Zhiwen Cao, Yixin Xie, Xingyu Jiang, Feng Tao, Yingjie Chen, Lin Li, Dongfang Liu

The existing MOTS studies face two critical challenges: 1) the published datasets inadequately capture the real-world complexity for network training to address various driving settings; 2) the working pipeline annotation tool is under-studied in the literature to improve the quality of MOTS learning examples.

Autonomous Driving Multi-Object Tracking +1

An Automated Portfolio Trading System with Feature Preprocessing and Recurrent Reinforcement Learning

no code implementations11 Oct 2021 Lin Li

We propose a novel portfolio trading system, which contains a feature preprocessing module and a trading module.

reinforcement-learning Reinforcement Learning (RL)

Financial Trading with Feature Preprocessing and Recurrent Reinforcement Learning

no code implementations11 Sep 2021 Lin Li

Financial trading aims to build profitable strategies to make wise investment decisions in the financial market.

reinforcement-learning Reinforcement Learning (RL)

Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation

no code implementations7 Sep 2021 Haoran Yang, Hongxu Chen, Lin Li, Philip S. Yu, Guandong Xu

They utilize simple and fixed schemes, like neighborhood information aggregation or mathematical calculation of vectors, to fuse the embeddings of different user behaviors to obtain a unified embedding to represent a user's behavioral patterns which will be used in downstream recommendation tasks.

Contrastive Learning Multi-Task Learning +1

XMUSPEECH System for VoxCeleb Speaker Recognition Challenge 2021

no code implementations6 Sep 2021 Jie Wang, Fuchuang Tong, Zhicong Chen, Lin Li, Qingyang Hong, Haodong Zhou

This paper describes the XMUSPEECH speaker recognition and diarisation systems for the VoxCeleb Speaker Recognition Challenge 2021.

Speaker Recognition

Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation

no code implementations3 Sep 2021 Jiahui Li, Kun Kuang, Lin Li, Long Chen, Songyang Zhang, Jian Shao, Jun Xiao

Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans.

Medical Diagnosis

Approximation Properties of Deep ReLU CNNs

no code implementations1 Sep 2021 Juncai He, Lin Li, Jinchao Xu

This paper focuses on establishing $L^2$ approximation properties for deep ReLU convolutional neural networks (CNNs) in two-dimensional space.

A Novel Dataset for Keypoint Detection of quadruped Animals from Images

1 code implementation31 Aug 2021 Prianka Banik, Lin Li, Xishuang Dong

In this paper, we studied the problem of localizing a generic set of keypoints across multiple quadruped or four-legged animal species from images.

Keypoint Detection

Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images

no code implementations9 Aug 2021 Zhongwei Xie, Ling Liu, Lin Li, Luo Zhong

This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images.

Cross-Modal Retrieval Retrieval +1

Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning

no code implementations2 Aug 2021 Zhongwei Xie, Ling Liu, Lin Li, Luo Zhong

This paper introduces a two-phase deep feature calibration framework for efficient learning of semantics enhanced text-image cross-modal joint embedding, which clearly separates the deep feature calibration in data preprocessing from training the joint embedding model.

Feature Engineering

Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service

1 code implementation2 Aug 2021 Zhongwei Xie, Ling Liu, Yanzhao Wu, Lin Li, Luo Zhong

We present a Multi-modal Semantics enhanced Joint Embedding approach (MSJE) for learning a common feature space between the two modalities (text and image), with the ultimate goal of providing high-performance cross-modal retrieval services.

Cross-Modal Retrieval Retrieval

OLR 2021 Challenge: Datasets, Rules and Baselines

no code implementations23 Jul 2021 Binling Wang, Wenxuan Hu, Jing Li, Yiming Zhi, Zheng Li, Qingyang Hong, Lin Li, Dong Wang, Liming Song, Cheng Yang

In addition to the Language Identification (LID) tasks, multilingual Automatic Speech Recognition (ASR) tasks are introduced to OLR 2021 Challenge for the first time.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Oriental Language Recognition (OLR) 2020: Summary and Analysis

no code implementations5 Jul 2021 Jing Li, Binling Wang, Yiming Zhi, Zheng Li, Lin Li, Qingyang Hong, Dong Wang

The fifth Oriental Language Recognition (OLR) Challenge focuses on language recognition in a variety of complex environments to promote its development.

Dialect Identification valid

SSC: Semantic Scan Context for Large-Scale Place Recognition

1 code implementation1 Jul 2021 Lin Li, Xin Kong, Xiangrui Zhao, Tianxin Huang, Yong liu

We also present a two-step global semantic ICP to obtain the 3D pose (x, y, yaw) used to align the point cloud to improve matching performance.

Translation Visual Place Recognition

An Integrated Framework for Two-pass Personalized Voice Trigger

no code implementations30 Jun 2021 Dexin Liao, Jing Li, Yiming Zhi, Song Li, Qingyang Hong, Lin Li

For the SV system, we proposed a multi-task learning network, where phonetic branch is trained with the character label of the utterance, and speaker branch is trained with the label of the speaker.

Keyword Spotting Multi-Task Learning +2

Phoneme-aware and Channel-wise Attentive Learning for Text DependentSpeaker Verification

no code implementations25 Jun 2021 Yan Liu, Zheng Li, Lin Li, Qingyang Hong

This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV).

Multi-Task Learning Text-Dependent Speaker Verification

SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure

no code implementations22 Jun 2021 Lin Li, Xin Kong, Xiangrui Zhao, Wanlong Li, Feng Wen, Hongbo Zhang, Yong liu

LiDAR-based SLAM system is admittedly more accurate and stable than others, while its loop closure detection is still an open issue.

3D Semantic Segmentation Loop Closure Detection

DMBGN: Deep Multi-Behavior Graph Networks for Voucher Redemption Rate Prediction

1 code implementation7 Jun 2021 Fengtong Xiao, Lin Li, Weinan Xu, Jingyu Zhao, Xiaofeng Yang, Jun Lang, Hao Wang

In this paper, we propose a Deep Multi-behavior Graph Networks (DMBGN) to shed light on this field for the voucher redemption rate prediction.


CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues

1 code implementation NAACL 2021 Bo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu

In this work, we propose a novel joint learning framework of modeling coreference resolution and query rewriting for complex, multi-turn dialogue understanding.

coreference-resolution Dialogue Understanding

ReLU Deep Neural Networks from the Hierarchical Basis Perspective

no code implementations10 May 2021 Juncai He, Lin Li, Jinchao Xu

We study ReLU deep neural networks (DNNs) by investigating their connections with the hierarchical basis method in finite element methods.

Measurement methods of radial flow in relativistic heavy-ion collisions

no code implementations4 Mar 2021 Peng Yang, Lin Li, Zhiming Li, Mingmei Xu, Yeyin Zhao, Yuanfang Wu

Radial flow can be directly extracted from the azimuthal distribution of mean transverse rapidity.

Nuclear Theory High Energy Physics - Phenomenology Nuclear Experiment

Manifold Learning-based Word Representation Refinement Incorporating Global and Local Information

no code implementations COLING 2020 Wenyu Zhao, Dong Zhou, Lin Li, Jinjun Chen

Our second method refines word representations by aligning original and re-fined embedding spaces based on local tangent space instead of performing weighted locally linear combination twice.

Semantic Similarity Semantic Textual Similarity +2

Direct Signal Separation Via Extraction of Local Frequencies with Adaptive Time-Varying Parameters

no code implementations5 Oct 2020 Lin Li, Charles K. Chui, Qingtang Jiang

In this paper, we propose an adaptive signal separation operation (ASSO) for effective and accurate separation of a single-channel blind-source multi-component signal, via introducing a time-varying parameter that adapts locally to IFs and using linear chirp (linear frequency modulation) signals to approximate components at each time instant.

Time Series Analysis

A Chirplet Transform-based Mode Retrieval Method for Multicomponent Signals with Crossover Instantaneous Frequencies

no code implementations4 Oct 2020 Lin Li, Ningning Han, Qingtang Jiang, Charles K. Chui

We use the chirplet transform (CT) to represent a multicomponent signal in the three-dimensional space of time, frequency and chirp rate and introduce a CT-based signal separation scheme (CT3S) to retrieve modes.


Analysis of Adaptive Synchrosqueezing Transform with a Time-varying Parameter

no code implementations22 Aug 2020 Jian Lu, Qingtang Jiang, Lin Li

The WSST with a time-varying parameter, called the adaptive WSST, was introduced very recently in the paper "Adaptive synchrosqueezing transform with a time-varying parameter for non-stationary signal separation".

AP20-OLR Challenge: Three Tasks and Their Baselines

no code implementations4 Jun 2020 Zheng Li, Miao Zhao, Qingyang Hong, Lin Li, Zhiyuan Tang, Dong Wang, Li-Ming Song, Cheng Yang

Based on Kaldi and Pytorch, recipes for i-vector and x-vector systems are also conducted as baselines for the three tasks.

Dialect Identification

Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT

1 code implementation Radiology 2020 Lin Li, Lixin Qin, Zeguo Xu, Youbing Yin, Xin Wang, Bin Kong, Junjie Bai, Yi Lu, Zhenghan Fang, Qi Song, Kunlin Cao, Daliang Liu, Guisheng Wang, Qizhong Xu, Xisheng Fang, Shiqin Zhang, Juan Xia, Jun Xia

Materials and Methods In this retrospective and multi-center study, a deep learning model, COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT exams for the detection of COVID-19.

COVID-19 Image Segmentation Specificity

A BERT based Sentiment Analysis and Key Entity Detection Approach for Online Financial Texts

no code implementations14 Jan 2020 Lingyun Zhao, Lin Li, Xinhao Zheng

Aiming at the issue, we propose a sentiment analysis and key entity detection approach based on BERT, which is applied in online financial text mining and public opinion analysis in social media.

Ensemble Learning Machine Reading Comprehension +5

Deep Visual Waterline Detection within Inland Marine Environment

no code implementations24 Nov 2019 Jing Huang, Hengfeng Miao, Lin Li, Yuanqiao Wen, Changshi Xiao

This paper attempts to find a solution to guarantee the effectiveness of waterline detection for inland maritime applications with general digital camera sensor.

When is ACL's Deadline? A Scientific Conversational Agent

no code implementations23 Nov 2019 Mohsen Mesgar, Paul Youssef, Lin Li, Dominik Bierwirth, Yihao Li, Christian M. Meyer, Iryna Gurevych

Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference visits, and preparing paper submissions using a unified interface based on natural language inputs and responses.

Choosing between Long and Short Word Forms in Mandarin

no code implementations WS 2019 Lin Li, Kees Van Deemter, Denis Paperno, Jingyu Fan

Between 80{\%} and 90{\%} of all Chinese words have long and short form such as 老虎/虎 (lao-hu/hu , tiger) (Duanmu:2013).

Social Influence-based Attentive Mavens Mining and Aggregative Representation Learning for Group Recommendation

no code implementations10 Aug 2019 Peipei Wang, Lin Li, Yi Yu, Guandong Xu

To tackle the issue of preference aggregation for group recommendation, we propose a novel attentive aggregation representation learning method based on sociological theory for group recommendation, namely SIAGR (short for "Social Influence-based Attentive Group Recommendation"), which takes attention mechanisms and the popular method (BERT) as the aggregation representation for group profile modeling.

Collaborative Filtering Decision Making +2

An Item Recommendation Approach by Fusing Images based on Neural Networks

no code implementations4 Jul 2019 Weibin Lin, Lin Li

There are rich formats of information in the network, such as rating, text, image, and so on, which represent different aspects of user preferences.

Collaborative Filtering Recommendation Systems

Combining Q&A Pair Quality and Question Relevance Features on Community-based Question Retrieval

no code implementations3 Jul 2019 Dong Li, Lin Li

The Q&A community has become an important way for people to access knowledge and information from the Internet.

Retrieval Translation

Using Context Information to Enhance Simple Question Answering

no code implementations27 Apr 2019 Lin Li, Mengjing Zhang, Zhaohui Chao, Jianwen Xiang

With the rapid development of knowledge bases(KBs), question answering(QA)based on KBs has become a hot research issue.

Question Answering

The combination of context information to enhance simple question answering

no code implementations9 Oct 2018 Zhaohui Chao, Lin Li

With the rapid development of knowledge base, question answering based on knowledge base has been a hot research issue.

Fact Selection Knowledge Base Question Answering

GPU based Parallel Optimization for Real Time Panoramic Video Stitching

no code implementations4 Oct 2018 Chengyao Du, Jingling Yuan, Jiansheng Dong, Lin Li, Mincheng Chen, Tao Li

In order to solve these problems, we propose a real-time panoramic video stitching framework. The framework we propose mainly consists of three algorithms, LORB image feature extraction algorithm, feature point matching algorithm based on LSH and GPU parallel video stitching algorithm based on CUDA. The experiment results show that the algorithm mentioned can improve the performance in the stages of feature extraction of images stitching and matching, the running speed of which is 11 times than that of the traditional ORB algorithm and 639 times than that of the traditional SIFT algorithm.

Image Stitching

Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings

no code implementations4 Oct 2018 Zhongwei Xie, Lin Li, Xian Zhong, Luo Zhong

In this paper, we propose an end-to-end neural network framework for image-to-video person reidentification by leveraging cross-modal embeddings learned from extra information. Concretely speaking, cross-modal embeddings from image captioning and video captioning models are reused to help learned features be projected into a coordinated space, where similarity can be directly computed.

Image Captioning Image-To-Video Person Re-Identification +2

Relational Network for Skeleton-Based Action Recognition

no code implementations7 May 2018 Wu Zheng, Lin Li, Zhao-Xiang Zhang, Yan Huang, Liang Wang

We introduce the Recurrent Relational Network to learn the spatial features in a single skeleton, followed by a multi-layer LSTM to learn the temporal features in the skeleton sequences.

Action Recognition Skeleton Based Action Recognition +1

Modeling Group Dynamics Using Probabilistic Tensor Decompositions

no code implementations24 Jun 2016 Lin Li, Ananthram Swami, Anna Scaglione

We propose a probabilistic modeling framework for learning the dynamic patterns in the collective behaviors of social agents and developing profiles for different behavioral groups, using data collected from multiple information sources.

Saliency Detection with Spaces of Background-based Distribution

no code implementations17 Mar 2016 Tong Zhao, Lin Li, Xinghao Ding, Yue Huang, Delu Zeng

In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background.

Saliency Detection

Sensing Subjective Well-being from Social Media

no code implementations15 Mar 2014 Bibo Hao, Lin Li, Rui Gao, Ang Li, Tingshao Zhu

Nowadays, people are motivated to share their experiences and feelings on social media, so we propose to sense SWB from the vast user generated data on social media.

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