no code implementations • EMNLP 2020 • Wei Song, Ziyao Song, Ruiji Fu, Lizhen Liu, Miaomiao Cheng, Ting Liu
First, we propose structural sentence positional encodings to explicitly represent sentence positions.
no code implementations • EMNLP 2020 • Wei Song, Kai Zhang, Ruiji Fu, Lizhen Liu, Ting Liu, Miaomiao Cheng
This paper proposes a pre-training based automated Chinese essay scoring method.
no code implementations • 20 Mar 2024 • Haoyu Liu, Yaoxian Song, Xuwu Wang, Zhu Xiangru, Zhixu Li, Wei Song, Tiefeng Li
Text-image retrieval research is needed to realize high-quality and efficient retrieval between different modalities.
no code implementations • 9 Mar 2024 • Junxiong Lin, Yan Wang, Zeng Tao, Boyang Wang, Qing Zhao, Haorang Wang, Xuan Tong, Xinji Mai, Yuxuan Lin, Wei Song, Jiawen Yu, Shaoqi Yan, Wenqiang Zhang
Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue.
1 code implementation • 29 Feb 2024 • Nuo Xu, Wen Wang, Rong Yang, Mengjie Qin, Zheyuan Lin, Wei Song, Chunlong Zhang, Jason Gu, Chao Li
Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations.
no code implementations • 9 Feb 2024 • Hao Song, Wei Lin, Wei Song, Man Wang
To enhance precision and comprehensiveness in identifying targets in electric power construction monitoring video, a novel target recognition algorithm utilizing infrared imaging is explored.
no code implementations • 5 Feb 2024 • Wei Song, Pei Li, Man Wang
To address the challenges of low detection accuracy and high false positive rates of transmission lines in UAV (Unmanned Aerial Vehicle) images, we explore the linear features and spatial distribution.
no code implementations • 16 Dec 2023 • Zhiwei Zha, Jiaan Wang, Zhixu Li, Xiangru Zhu, Wei Song, Yanghua Xiao
To collect concept-image and concept-description alignments, we propose a context-aware multi-modal symbol grounding approach that considers context information in existing large-scale image-text pairs with respect to each concept.
no code implementations • 7 Dec 2023 • Yongqi Dong, Xingmin Lu, Ruohan Li, Wei Song, Bart van Arem, Haneen Farah
In conclusion, the proposed pipeline, with its incorporation of self-supervised pre-training using MiM and other advanced deep learning techniques, emerges as a robust solution for enhancing the accuracy and efficiency of lane rendering image anomaly detection in digital navigation systems.
1 code implementation • 20 Sep 2023 • Yike Wu, Nan Hu, Sheng Bi, Guilin Qi, Jie Ren, Anhuan Xie, Wei Song
To this end, we propose an answer-sensitive KG-to-Text approach that can transform KG knowledge into well-textualized statements most informative for KGQA.
1 code implementation • IEEE Transactions on Image Processing 2023 • Fangtai Guo, Tianlei Jin, Shiqiang Zhu, Xiangming Xi, Wen Wang, Qiwei Meng, Wei Song, and Jiakai Zhu
Human Action Recognition plays a driving engine of many human-computer interaction applications.
Ranked #19 on Action Recognition on NTU RGB+D
no code implementations • 17 Aug 2023 • Wei Song, Jun Zhou, Mingjie Wang, Hongchen Tan, Nannan Li, Xiuping Liu
In this work, we propose a novel multimodal fusion network for point cloud completion, which can simultaneously fuse visual and textual information to predict the semantic and geometric characteristics of incomplete shapes effectively.
no code implementations • 13 Jul 2023 • Mario Di Mauro, Giovanni Galatro, Fabio Postiglione, Wei Song, Antonio Liotta
Predicting the behavior of real-time traffic (e. g., VoIP) in mobility scenarios could help the operators to better plan their network infrastructures and to optimize the allocation of resources.
no code implementations • 6 Apr 2023 • Xinyue Li, Jian Wang, Wei Song, Yanling Du, Zhixiang Liu
The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods.
no code implementations • CVPR 2023 • Tianlei Jin, Fangtai Guo, Qiwei Meng, Shiqiang Zhu, Xiangming Xi, Wen Wang, Zonghao Mu, Wei Song
Therefore, at the context level, we can produce diverse context descriptions by using a context augmentation method based on the original dataset.
no code implementations • MM '22: Proceedings of the 30th ACM International Conference on Multimedia 2022 • Yan Wang, Yixuan Sun, Wei Song, Shuyong Gao, Yiwen Huang, Zhaoyu Chen, Weifeng Ge, and Wenqiang Zhang
To obtain consistent prediction probabilities from the dual path, we further propose a dual path regularization loss, aiming to minimize the divergence between the distributions of two-path embeddings.
Ranked #13 on Dynamic Facial Expression Recognition on DFEW
Dynamic Facial Expression Recognition Representation Learning
no code implementations • 27 Jul 2022 • Fiseha B. Tesema, Zheyuan Lin, Shiqiang Zhu, Wei Song, Jason Gu, Hong Wu
After fusion, one BiGRU layer is attached to model the joint temporal dynamics.
1 code implementation • 8 Jul 2022 • Wen Wang, Shunda Hu, Shiqiang Zhu, Wei Song, Zheyuan Lin, Tianlei Jin, Zonghao Mu, Yuanhai Zhou
A service robot serving safely and politely needs to track the surrounding people robustly, especially for Tour-Guide Robot (TGR).
no code implementations • ACL 2021 • Jiefu Gong, Xiao Hu, Wei Song, Ruiji Fu, Zhichao Sheng, Bo Zhu, Shijin Wang, Ting Liu
IFlyEA provides multi-level and multi-dimension analytical modules for essay assessment.
no code implementations • ACL 2021 • Wei Song, Shuhui Zhou, Ruiji Fu, Ting Liu, Lizhen Liu
Correct natural language understanding requires computers to distinguish the literal and metaphorical senses of a word.
2 code implementations • 26 Mar 2021 • Minghao Liu, Shengqi Ren, Siyuan Ma, Jiahui Jiao, Yizhou Chen, Zhiguang Wang, Wei Song
In this work, we explored a simple extension of the current Transformer Networks with gating, named Gated Transformer Networks (GTN) for the multivariate time series classification problem.
no code implementations • 16 Feb 2021 • Alejandra Castro, Victor Godet, Joan Simón, Wei Song, Boyang Yu
Our aim is to characterise those perturbations that are responsible for the deviations away from extremality, and to contrast them with the linearized perturbations treated in the Newman-Penrose formalism.
High Energy Physics - Theory General Relativity and Quantum Cosmology
no code implementations • 6 Nov 2020 • Guanghui Xu, Wei Song, Zhengchen Zhang, Chao Zhang, Xiaodong He, BoWen Zhou
Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech.
3 code implementations • 6 Mar 2020 • Wei Song, Xuezixiang Li, Sadia Afroz, Deepali Garg, Dmitry Kuznetsov, Heng Yin
However, it is well-known that machine learning models are vulnerable to adversarial examples (AEs).
Cryptography and Security
1 code implementation • 19 Dec 2019 • Jiali Zeng, Linfeng Song, Jinsong Su, Jun Xie, Wei Song, Jiebo Luo
Simile recognition is to detect simile sentences and to extract simile components, i. e., tenors and vehicles.
1 code implementation • 7 Jul 2019 • Yan Wang, Wei Song, Giancarlo Fortino, Lizhe Qi, Wenqiang Zhang, Antonio Liotta
Underwater images play a key role in ocean exploration, but often suffer from severe quality degradation due to light absorption and scattering in water medium.
no code implementations • 12 Apr 2019 • Liumeng Xue, Wei Song, Guanghui Xu, Lei Xie, Zhizheng Wu
When deploying a Chinese neural text-to-speech (TTS) synthesis system, one of the challenges is to synthesize Chinese utterances with English phrases or words embedded.
no code implementations • EMNLP 2018 • Lizhen Liu, Xiao Hu, Wei Song, Ruiji Fu, Ting Liu, Guoping Hu
Simile is a special type of metaphor, where comparators such as like and as are used to compare two objects.
no code implementations • COLING 2018 • Lizhen Liu, Donghai Zhang, Wei Song
Humor recognition is an interesting and challenging task in natural language processing.
no code implementations • ACL 2018 • Lizhen Liu, Donghai Zhang, Wei Song
Humor is one of the most attractive parts in human communication.
no code implementations • WS 2018 • Ruiji Fu, Zhengqi Pei, Jiefu Gong, Wei Song, Dechuan Teng, Wanxiang Che, Shijin Wang, Guoping Hu, Ting Liu
This paper describes our system at NLPTEA-2018 Task {\#}1: Chinese Grammatical Error Diagnosis.
no code implementations • SEMEVAL 2018 • Zhimin Chen, Wei Song, Lizhen Liu
The task is to select the correct warrant that explains reasoning of a particular argument consisting of a claim and a reason.
no code implementations • ACL 2017 • Wei Song, Dong Wang, Ruiji Fu, Lizhen Liu, Ting Liu, Guoping Hu
Evaluation results show that discourse modes can be identified automatically with an average F1-score of 0. 7.
no code implementations • COLING 2016 • Wei Song, Ruiji Fu, Lizhen Liu, Hanshi Wang, Ting Liu
More importantly, we uncover the anecdote implication, which reveals the meaning and topic of an anecdote.
no code implementations • COLING 2016 • Wei Song, Tong Liu, Ruiji Fu, Lizhen Liu, Hanshi Wang, Ting Liu
Parallelism is an important rhetorical device.
1 code implementation • 24 Oct 2016 • Zhiguang Wang, Wei Song, Lu Liu, Fan Zhang, Junxiao Xue, Yangdong Ye, Ming Fan, Mingliang Xu
We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series.
no code implementations • 8 Jun 2015 • Wei Song, Zhiguang Wang, Yangdong Ye, Ming Fan
Our work provides an analytical framework with several statistical tools to analyze, evaluate and further improve the symbolic dynamics for knowledge discovery in time series.