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
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.
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.
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.
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.
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 • 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 • 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 • 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 #3 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
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 • 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 • 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 • 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, 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.
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 • 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