Search Results for author: Jingyu Wang

Found 54 papers, 22 papers with code

Modeling Aspect Correlation for Aspect-based Sentiment Analysis via Recurrent Inverse Learning Guidance

no code implementations COLING 2022 Longfeng Li, Haifeng Sun, Qi Qi, Jingyu Wang, Jing Wang, Jianxin Liao

Second, we propose Inverse Learning Guidance to improve the selection of aspect feature by considering aspect correlation, which provides more useful information to determine polarity.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1

ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Data

no code implementations15 May 2025 Chengsen Wang, Qi Qi, Zhongwen Rao, Lujia Pan, Jingyu Wang, Jianxin Liao

To address the scarcity of event-series paired data, we propose a decoupled framework: an LLM is employed to transform textual events into revision instructions, which are then used to steer the output of TSFM.

Language Modeling Language Modelling +4

Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting

no code implementations1 May 2025 Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jianxin Liao

Time series forecasting holds significant importance across various industries, including finance, transportation, energy, healthcare, and climate.

Missing Values Multivariate Time Series Forecasting +1

Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models

1 code implementation27 Feb 2025 Huazheng Wang, Yongcheng Jing, Haifeng Sun, Yingjie Wang, Jingyu Wang, Jianxin Liao, DaCheng Tao

In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation--ensuring that models forget not only specific training samples but also related implicit knowledge.

Machine Unlearning

NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches

no code implementations18 Feb 2025 Penghui Zhang, Hua Zhang, Yuqi Dai, Cheng Zeng, Jingyu Wang, Jianxin Liao

Specifically, NTP-INT consists of three modules: network traffic prediction module, network pruning module, and probe path planning module.

Deep Reinforcement Learning Graph Neural Network +2

Unhackable Temporal Rewarding for Scalable Video MLLMs

no code implementations17 Feb 2025 En Yu, Kangheng Lin, Liang Zhao, Yana Wei, Zining Zhu, Haoran Wei, Jianjian Sun, Zheng Ge, Xiangyu Zhang, Jingyu Wang, Wenbing Tao

In the pursuit of superior video-processing MLLMs, we have encountered a perplexing paradox: the "anti-scaling law", where more data and larger models lead to worse performance.

Deep Generative Model-Aided Power System Dynamic State Estimation and Reconstruction with Unknown Control Inputs or Data Distributions

no code implementations6 Jan 2025 Jianhua Pei, Ping Wang, Jingyu Wang, Dongyuan Shi

The proposed approach employs an encoder-decoder architecture to estimate unknown control input variables, a robust encoder to mitigate the impact of bad PMU data, and latent diffusion model to address communication issues in centralized DSE.

State Estimation

Pose-Guided Temporal Enhancement for Robust Low-Resolution Hand Reconstruction

no code implementations CVPR 2025 Kaixin Fan, Pengfei Ren, Jingyu Wang, Haifeng Sun, Qi Qi, Zirui Zhuang, Jianxin Liao

We introduce Triplane Features, a dense representation with 3D spatial awareness, to bridge the gap between the joint features and visual features that are misaligned in terms of representation form and semantics.

ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data

1 code implementation16 Dec 2024 Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jinming Wu, Lei Zhang, Jianxin Liao

In this paper, we innovatively model time series as a foreign language and construct ChatTime, a unified framework for time series and text processing.

Language Modeling Language Modelling +3

MEGL: Multimodal Explanation-Guided Learning

no code implementations20 Nov 2024 Yifei Zhang, Tianxu Jiang, Bo Pan, Jingyu Wang, Guangji Bai, Liang Zhao

A Visual Explanation Distribution Consistency loss further reinforces visual coherence by aligning the generated visual explanations with dataset-level patterns, enabling the model to effectively learn from incomplete multimodal supervision.

image-classification Image Classification

DRL Optimization Trajectory Generation via Wireless Network Intent-Guided Diffusion Models for Optimizing Resource Allocation

no code implementations18 Oct 2024 Junjie Wu, Xuming Fang, Dusit Niyato, Jiacheng Wang, Jingyu Wang

This model can be generated and fine-tuned in real time to achieve the objective and meet the constraints of target intent networks, significantly reducing state information exposure during wireless communication.

Deep Reinforcement Learning

Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection

1 code implementation11 Oct 2024 Yuanyi Wang, Haifeng Sun, Chengsen Wang, Mengde Zhu, Jingyu Wang, Wei Tang, Qi Qi, Zirui Zhuang, Jianxin Liao

To capitalize on this insight, we introduce MADGA (MTS Anomaly Detection via Graph Alignment), which redefines anomaly detection as a graph alignment (GA) problem that explicitly utilizes interdependencies for anomaly detection.

Anomaly Detection Time Series +1

RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering

no code implementations30 Sep 2024 Deheng Zhang, Jingyu Wang, Shaofei Wang, Marko Mihajlovic, Sergey Prokudin, Hendrik P. A. Lensch, Siyu Tang

Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.

Inverse Rendering

Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective

1 code implementation27 Sep 2024 Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jinming Wu, Jianxin Liao

Time series forecasting has played a pivotal role across various industries, including finance, transportation, energy, healthcare, and climate.

Time Series Time Series Forecasting

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models

1 code implementation22 Aug 2024 Shenglin Zhang, Pengtian Zhu, Minghua Ma, Jiagang Wang, Yongqian Sun, Dongwen Li, Jingyu Wang, Qianying Guo, Xiaolei Hua, Lin Zhu, Dan Pei

Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge.

Question Answering

OutlierTune: Efficient Channel-Wise Quantization for Large Language Models

no code implementations27 Jun 2024 Jinguang Wang, Yuexi Yin, Haifeng Sun, Qi Qi, Jingyu Wang, Zirui Zhuang, Tingting Yang, Jianxin Liao

The pre-execution of dequantization updates the model weights by the activation scaling factors, avoiding the internal scaling and costly additional computational overheads brought by the per-channel activation quantization.

Quantization

Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids

no code implementations15 Jun 2024 Yiye Zou, Tianyu Li, Lin Lu, Jingyu Wang, Shufan Zou, Laiping Zhang, Xiaogang Deng

To address this issue, \blueText{graphs and graph networks are used} to learn flow representations across multi-block-structured grids.

MLS-Track: Multilevel Semantic Interaction in RMOT

no code implementations18 Apr 2024 Zeliang Ma, Song Yang, Zhe Cui, Zhicheng Zhao, Fei Su, Delong Liu, Jingyu Wang

The new trend in multi-object tracking task is to track objects of interest using natural language.

Multi-Object Tracking

Object-level Copy-Move Forgery Image Detection based on Inconsistency Mining

no code implementations31 Mar 2024 Jingyu Wang, Niantai Jing, Ziyao Liu, Jie Nie, Yuxin Qi, Chi-Hung Chi, Kwok-Yan Lam

Additionally, we extract inconsistent regions between coarse similar regions obtained through self-correlation calculations and regions composed of prototypes.

Forgery Image Detection Object

An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation

no code implementations13 Feb 2024 Xin Jin, Wu Zhou, Jingyu Wang, Duo Xu, Yongsen Zheng

In order to improve the quality of AI music generation and further guide computer music production, synthesis, recommendation and other tasks, we use Birkhoff's aesthetic measure to design a aesthetic model, objectively measuring the aesthetic beauty of music, and form a recommendation list according to the aesthetic feeling of music.

Music Generation Music Recommendation

Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation

1 code implementation5 Feb 2024 Yuanyi Wang, Wei Tang, Haifeng Sun, Zirui Zhuang, Xiaoyuan Fu, Jingyu Wang, Qi Qi, Jianxin Liao

In this paper, we present a propagation perspective to analyze weakly supervised EA and explain the existing aggregation-based EA models.

Entity Alignment Knowledge Graphs

Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment

1 code implementation31 Jan 2024 Yuanyi Wang, Haifeng Sun, Jiabo Wang, Jingyu Wang, Wei Tang, Qi Qi, Shaoling Sun, Jianxin Liao

This study introduces a novel approach, DESAlign, which addresses these issues by applying a theoretical framework based on Dirichlet energy to ensure semantic consistency.

Attribute Graph Learning +3

Gradient Flow of Energy: A General and Efficient Approach for Entity Alignment Decoding

1 code implementation23 Jan 2024 Yuanyi Wang, Haifeng Sun, Jingyu Wang, Qi Qi, Shaoling Sun, Jianxin Liao

However, the decoding process in EA - essential for effective operation and alignment accuracy - has received limited attention and remains tailored to specific datasets and model architectures, necessitating both entity and additional explicit relation embeddings.

Entity Alignment Entity Embeddings +4

Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning

no code implementations CVPR 2024 Menghao Zhang, Jingyu Wang, Qi Qi, Haifeng Sun, Zirui Zhuang, Pengfei Ren, Ruilong Ma, Jianxin Liao

ecent progress in video anomaly detection suggests that the features of appearance and motion play crucial roles in distinguishing abnormal patterns from normal ones.

Anomaly Detection Contrastive Learning +2

Detection and Imputation based Two-Stage Denoising Diffusion Power System Measurement Recovery under Cyber-Physical Uncertainties

no code implementations7 Dec 2023 Jianhua Pei, Jingyu Wang, Dongyuan Shi, Ping Wang

Power system cyber-physical uncertainties, including measurement ambiguities stemming from cyber attacks and data losses, along with system uncertainties introduced by massive renewables and complex dynamics, reduce the likelihood of enhancing the quality of measurements.

Anomaly Detection Denoising +1

Extracting Physical Causality from Measurements to Detect and Localize False Data Injection Attacks

no code implementations21 Sep 2023 Shengyang Wu, Jingyu Wang, Dongyuan Shi

They are sensitive to the violation of physical laws caused by FDIA, but tend to remain stable with the drift of system operating points.

Causal Inference Graph Attention

Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies

1 code implementation15 Aug 2023 Yilun Liu, Shimin Tao, Weibin Meng, Jingyu Wang, Wenbing Ma, Yanqing Zhao, Yuhang Chen, Hao Yang, Yanfei Jiang, Xun Chen

LogPrompt employs large language models (LLMs) to perform online log analysis tasks via a suite of advanced prompt strategies tailored for log tasks, which enhances LLMs' performance by up to 380. 7% compared with simple prompts.

Anomaly Detection Log Parsing +1

Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource

no code implementations21 Jun 2023 Xiang Yang, Dezhi Chen, Qi Qi, Jingyu Wang, Haifeng Sun, Jianxin Liao, Song Guo

Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices.

Edge-computing

Automatic Generation of Topology Diagrams for Strongly-Meshed Power Transmission Systems

1 code implementation15 Mar 2023 Jingyu Wang, Jinfu Chen, Dongyuan Shi, Xianzhong Duan

This paper proposes an integrated framework for generating aesthetically-pleasing topology diagrams for power transmission systems.

Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image

1 code implementation ICCV 2023 Pengfei Ren, Chao Wen, Xiaozheng Zheng, Zhou Xue, Haifeng Sun, Qi Qi, Jingyu Wang, Jianxin Liao

On the other hand, there are complex spatial relationship between interacting hands, which significantly increases the solution space of hand poses and increases the difficulty of network learning.

3D Hand Pose Estimation 3D Interacting Hand Pose Estimation

HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning

1 code implementation ICCV 2023 Xiaozheng Zheng, Chao Wen, Zhou Xue, Pengfei Ren, Jingyu Wang

Recent advancements in 3D hand pose estimation have shown promising results, but its effectiveness has primarily relied on the availability of large-scale annotated datasets, the creation of which is a laborious and costly process.

3D Hand Pose Estimation Self-Supervised Learning

Universal adaptive optics for microscopy through embedded neural network control

no code implementations6 Jan 2023 Qi Hu, Martin Hailstone, Jingyu Wang, Matthew Wincott, Danail Stoychev, Huriye Atilgan, Dalia Gala, Tai Chaiamarit, Richard M. Parton, Jacopo Antonello, Adam M. Packer, Ilan Davis, Martin J. Booth

Unlike previous ML methods, we used a bespoke neural network (NN) architecture, designed using physical understanding of image formation, that was embedded in the control loop of the microscope.

Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding

1 code implementation29 Jul 2022 Jiachang Hao, Haifeng Sun, Pengfei Ren, Jingyu Wang, Qi Qi, Jianxin Liao

Our framework introduces two auxiliary tasks, cross-modal matching and temporal order discrimination, to promote the grounding model training.

Language-Based Temporal Localization Sentence

Approximation of Images via Generalized Higher Order Singular Value Decomposition over Finite-dimensional Commutative Semisimple Algebra

1 code implementation1 Feb 2022 Liang Liao, Sen Lin, Lun Li, Xiuwei Zhang, Song Zhao, Yan Wang, Xinqiang Wang, Qi Gao, Jingyu Wang

Higher order singular value decomposition (HOSVD) extends the SVD and can approximate higher order data using sums of a few rank-one components.

Mining Multi-View Information: A Strong Self-Supervised Framework for Depth-Based 3D Hand Pose and Mesh Estimation

1 code implementation CVPR 2022 Pengfei Ren, Haifeng Sun, Jiachang Hao, Jingyu Wang, Qi Qi, Jianxin Liao

However, these methods ignore the rich semantic information in each view and ignore the complex dependencies between different regions of different views.

3D Hand Pose Estimation

CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference

no code implementations6 Jul 2021 Zhiyu Chen, Zhanghao Yu, Qing Jin, Yan He, Jingyu Wang, Sheng Lin, Dai Li, Yanzhi Wang, Kaiyuan Yang

A compact, accurate, and bitwidth-programmable in-memory computing (IMC) static random-access memory (SRAM) macro, named CAP-RAM, is presented for energy-efficient convolutional neural network (CNN) inference.

Question-Driven Span Labeling Model for Aspect–Opinion Pair Extraction

no code implementations AAAI 2021 Lei Gao, Yulong Wang, Tongcun Liu, Jingyu Wang, Lei Zhang, Jianxin Liao

Specifically, we divide the AOPE task into aspect term extraction (ATE) and aspect-specified opinion extraction (ASOE) subtasks; we first extract all the candidate aspect terms and then the corresponding opinion words given the aspect term.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction

no code implementations5 Nov 2020 Xuanzhao Wang, Zhengping Che, Bo Jiang, Ning Xiao, Ke Yang, Jian Tang, Jieping Ye, Jingyu Wang, Qi Qi

In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.

Anomaly Detection Prediction +1

AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation

1 code implementation19 Jul 2020 Weiting Huang, Pengfei Ren, Jingyu Wang, Qi Qi, Haifeng Sun

In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods.

3D Hand Pose Estimation regression

Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis

no code implementations ACL 2020 Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao

To tackle these problems, we design a post-training procedure, which contains the target domain masked language model task and a novel domain-distinguish pre-training task.

Language Modeling Language Modelling +3

Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification

no code implementations IJCNLP 2019 Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, Ming Liu

Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context.

Classification General Classification +3

Investigating Capsule Network and Semantic Feature on Hyperplanes for Text Classification

no code implementations IJCNLP 2019 Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Chun Wang, Bing Ma

It has been demonstrated that multiple senses of a word actually reside in linear superposition within the word embedding so that specific senses can be extracted from the original word embedding.

General Classification text-classification +1

OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks

1 code implementation CVPR 2019 Jiashi Li, Qi Qi, Jingyu Wang, Ce Ge, Yujian Li, Zhangzhang Yue, Haifeng Sun

Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage.

Fewer is More: Image Segmentation Based Weakly Supervised Object Detection with Partial Aggregation

no code implementations BMVC 2018 Ce Ge, Jingyu Wang, Qi Qi, Haifeng Sun, Jianxin Liao

As most weakly supervised object detection methods are based on pre-generated proposals, they often show two false detections: (i) group multiple object instances with one bounding box, and (ii) focus on only parts rather than the whole objects.

Image Segmentation Object +3

Chinese/English mixed Character Segmentation as Semantic Segmentation

no code implementations7 Nov 2016 Huabin Zheng, Jingyu Wang, Zhengjie Huang, Yang Yang, Rong pan

We take advantage of the successful architecture called fully convolutional networks (FCN) in the field of semantic segmentation.

Diversity Optical Character Recognition (OCR) +3

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