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
no code implementations • 15 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.
no code implementations • 1 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.
no code implementations • 17 Apr 2025 • Jingyu Wang, Donglin Xie, Jingying Ma, Yunliang Sun, Linyan Zhang, Rui Bai, Zelin Tu, Liyue Xu, Jun Wei, Jingjing Yang, Yanan Liu, Huijie Yi, Bing Zhou, Long Zhao, Xueli Zhang, Mengling Feng, Xiaosong Dong, Guoli Liu, Fang Han, Shenda Hong
FHR changes were significantly associated with maternal hypoxia, primarily characterized by accelerations.
1 code implementation • 10 Apr 2025 • En Yu, Kangheng Lin, Liang Zhao, Jisheng Yin, Yana Wei, Yuang Peng, Haoran Wei, Jianjian Sun, Chunrui Han, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Jingyu Wang, Wenbing Tao
In this work, we return to the fundamentals and explore the effects of RL on different perception tasks.
1 code implementation • 3 Mar 2025 • Yuhan Jing, Jingyu Wang, Lei Zhang, Haifeng Sun, Bo He, Zirui Zhuang, Chengsen Wang, Qi Qi, Jianxin Liao
Furthermore, we build a special scenario dataset to compare the characteristics of different evaluation methods.
1 code implementation • 27 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.
no code implementations • 18 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.
no code implementations • 17 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.
no code implementations • 16 Jan 2025 • Yan Li, Jingyu Wang, Jiankang Zhang, Huaiqiang Li, Longfei Ren, Yinhong Li, Dongyuan Shi, Xianzhong Duan
Searching for the Extreme Operating Conditions (EOCs) is one of the core problems of power system relay protection setting calculation.
no code implementations • 6 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.
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.
1 code implementation • 16 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.
no code implementations • 20 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.
no code implementations • 18 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.
1 code implementation • 11 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.
no code implementations • 30 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.
1 code implementation • 27 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.
1 code implementation • 22 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.
no code implementations • 27 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.
no code implementations • 15 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.
no code implementations • 18 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.
no code implementations • 31 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.
no code implementations • 13 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.
1 code implementation • 5 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.
1 code implementation • 3 Feb 2024 • Yanhua Zhang, Ke Zhang, Jingyu Wang, Yulin Wu, Wuwei Wang
Real-time semantic segmentation is a crucial research for real-world applications.
1 code implementation • 31 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.
1 code implementation • 23 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.
no code implementations • CVPR 2024 • Pengfei Ren, Yuanyuan Gao, Haifeng Sun, Qi Qi, Jingyu Wang, Jianxin Liao
Category-agnostic pose estimation (CAPE) aims to predict the pose of a query image based on few support images with pose annotations.
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.
1 code implementation • 21 Dec 2023 • Lvyang Yang, Jiankang Zhang, Huaiqiang Li, Longfei Ren, Chen Yang, Jingyu Wang, Dongyuan Shi
Existing computer vision approaches for digitizing engineering drawings typically assume the input drawings have high quality.
no code implementations • 7 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.
no code implementations • 21 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.
1 code implementation • 15 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.
1 code implementation • 26 Jul 2023 • Huazheng Wang, Daixuan Cheng, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Jing Wang, Cong Liu
It shows that finetuning PLMs with diffusion degrades the reconstruction ability on OOD data.
no code implementations • 21 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.
1 code implementation • 15 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.
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.
Ranked #4 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
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.
no code implementations • 6 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.
1 code implementation • 29 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.
1 code implementation • 1 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.
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.
no code implementations • 6 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.
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
no code implementations • 5 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.
no code implementations • Computers in Industry 2020 • Ce Ge, Jing Wang, Jingyu Wang, Qi Qi, Haifeng Sun, Jianxin Liao:
With the recent progress of deep learning, advanced industrial object detectors are built for smart industrial applications.
Ranked #28 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
1 code implementation • 19 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.
Ranked #1 on
Hand Pose Estimation
on HANDS 2017
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.
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.
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.
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.
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.
Ranked #31 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
no code implementations • 7 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.