no code implementations • CCL 2020 • Zhengwei Lv, Lei Yang, Zhizhong Shi, Xiao Liang, Tao Lei, Duoxing Liu
阅读理解问答系统是利用语义理解等自然语言处理技术, 根据输入问题, 对非结构化文档数据进行分析, 生成一个答案, 具有很高的研究和应用价值。在垂直领域应用过程中, 阅读理解问答数据标注成本高且用户问题表达复杂多样, 使得阅读理解问答系统准确率低、鲁棒性差。针对这一问题, 本文提出一种面向垂直领域的阅读理解问答数据的增强方法, 该方法基于真实用户问题, 构造阅读理解训练数据, 一方面降低标注成本, 另一方面增加训练数据多样性, 提升模型的准确率和鲁棒性。本文用汽车领域数据对该方法进行实验验证, 其结果表明该方法对垂直领域阅读理解模型的准确率和鲁棒性均能有效提升。
no code implementations • 20 Mar 2024 • Mengyu Yang, Ye Tian, Lanshan Zhang, Xiao Liang, Xuming Ran, Wendong Wang
Recently, prompt-based methods have emerged as a new alternative `parameter-efficient fine-tuning' paradigm, which only fine-tunes a small number of additional parameters while keeping the original model frozen.
no code implementations • 27 Feb 2024 • Ming Ye, Xiao Liang, Cunhua Pan, Yinfei Xu, Ming Jiang, ChunGuo Li
The mixed line-of-sight (LoS) and non-line-of-sight (NLoS) XL-MIMO near-field channel model is adopted to describe the XL-MIMO near-field channel accurately.
1 code implementation • 26 Oct 2023 • Xiao Liang, Tao Shi, Yaoyuan Liang, Te Tao, Shao-Lun Huang
In this paper, we propose DiffusionVG, a novel framework with diffusion models that formulates video grounding as a conditional generation task, where the target span is generated from Gaussian noise inputs and interatively refined in the reverse diffusion process.
1 code implementation • 25 Oct 2023 • Tao Shi, Xiao Liang, Yaoyuan Liang, Xinyi Tong, Shao-Lun Huang
To address these challenges, we propose an efficient and model-agnostic SCL framework named Supervised Sample-Label Contrastive Learning with Soft-HGR Maximal Correlation (SSLCL), which eliminates the need for a large batch size and can be seamlessly integrated with existing ERC models without introducing any model-specific assumptions.
no code implementations • 10 Oct 2023 • Tong Guo, Xuanping Li, Haitao Yang, Xiao Liang, Yong Yuan, Jingyou Hou, Bingqing Ke, Chao Zhang, Junlin He, Shunyu Zhang, Enyun Yu, WenWu
The overall historical behaviors are various but noisy while search behaviors are always sparse.
no code implementations • 25 Aug 2023 • Jiawen Xie, Pengyu Cheng, Xiao Liang, Yong Dai, Nan Du
Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the input sequence length.
no code implementations • 6 Aug 2023 • Kareem Eltouny, Seyedomid Sajedi, Xiao Liang
Visual inspection is predominantly used to evaluate the state of civil structures, but recent developments in unmanned aerial vehicles (UAVs) and artificial intelligence have increased the speed, safety, and reliability of the inspection process.
no code implementations • 30 Jul 2023 • Sibo Tian, Minghui Zheng, Xiao Liang
Predicting human motion plays a crucial role in ensuring a safe and effective human-robot close collaboration in intelligent remanufacturing systems of the future.
no code implementations • 20 Jul 2023 • Nikhil U. Shinde, Xiao Liang, Florian Richter, Michael C. Yip
Additionally these methods are reliant on the availability of large training datasets to converge to useful solutions.
1 code implementation • 24 May 2023 • Xiao Liang, Shan Lin, Fei Liu, Dimitri Schreiber, Michael Yip
Recent Deep Learning methods have shown promising accuracy and speedup for registering a pair of medical images.
1 code implementation • 5 Apr 2023 • Yunxiang Li, Hua-Chieh Shao, Xiao Liang, Liyuan Chen, RuiQi Li, Steve Jiang, Jing Wang, You Zhang
However, for medical image translation, the existing diffusion models are deficient in accurately retaining structural information since the structure details of source domain images are lost during the forward diffusion process and cannot be fully recovered through learned reverse diffusion, while the integrity of anatomical structures is extremely important in medical images.
no code implementations • 16 Feb 2023 • Jiaxin Cheng, Xiao Liang, Xingjian Shi, Tong He, Tianjun Xiao, Mu Li
Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts.
no code implementations • 8 Feb 2023 • Jinglun Yu, Muhan Shao, Zhangxing Bian, Xiao Liang, Jiachen Zhuo, Maureen Stone, Jerry L. Prince
Accurate tongue motion estimation is essential for tongue function evaluation.
no code implementations • 3 Feb 2023 • Anjali Balagopal, Michael Dohopolski, Young Suk Kwon, Steven Montalvo, Howard Morgan, Ti Bai, Dan Nguyen, Xiao Liang, Xinran Zhong, Mu-Han Lin, Neil Desai, Steve Jiang
Conclusion: The proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.
no code implementations • 6 Jan 2023 • Liu Liu, Yukai Lin, Xiao Liang, Qichao Xu, Miao Jia, Yangdong Liu, Yuxiang Wen, Wei Luo, Jiangwei Li
Second, a single-image-based localization pipeline (retrieval--matching--PnP) is performed to estimate 6-DoF camera poses for each query image, one for each 3D map.
no code implementations • 21 Oct 2022 • Seyedomid Sajedi, Xiao Liang
The developed strategy for spatio-temporal analysis of signals enhances the robustness of damage diagnosis frameworks that utilize deep learning for monitoring lifeline structures.
no code implementations • 21 Oct 2022 • Kareem Eltouny, Seyedomid Sajedi, Xiao Liang
Visual inspection is the predominant technique for evaluating the condition of civil infrastructure.
no code implementations • 7 Jun 2022 • Xiao Liang, Howard Morgan, Ti Bai, Michael Dohopolski, Dan Nguyen, Steve Jiang
We found that DL-based direct segmentation on CBCT trained with pseudo labels and without influencer volumes shows poor performance compared to DIR-based segmentation.
no code implementations • 18 Apr 2022 • Xun Wang, Bingqing Ke, Xuanping Li, Fangyu Liu, Mingyu Zhang, Xiao Liang, Qiushi Xiao, Cheng Luo, Yue Yu
This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching.
no code implementations • 4 Apr 2022 • Yusuke Takimoto, Hiroyuki Sato, Hikari Takehara, Keishiro Uragaki, Takehiro Tawara, Xiao Liang, Kentaro Oku, Wataru Kishimoto, Bo Zheng
HardSoftRas, our novel rendering process, is designed for inverse rendering with a graphics pipeline.
no code implementations • 8 Mar 2022 • Ti Bai, MuHan Lin, Xiao Liang, Biling Wang, Michael Dohopolski, Bin Cai, Dan Nguyen, Steve Jiang
A test time optimization (TTO) technique was proposed to further improve the DL models' performance.
no code implementations • 8 Feb 2022 • Xiao Liang, Jaehee Chun, Howard Morgan, Ti Bai, Dan Nguyen, Justin C. Park, Steve Jiang
Firstly, we trained a population model with 200 patients, and then applied TTO to the remaining 39 test patients by refining the trained population model to obtain 39 individualized models.
1 code implementation • 29 Oct 2021 • Yeshu Li, Jonathan Cui, Yilun Sheng, Xiao Liang, Jingdong Wang, Eric I-Chao Chang, Yan Xu
To address these issues, we propose to adopt a full volume framework, which feeds the full volume brain image into the segmentation network and directly outputs the segmentation result for the whole brain volume.
1 code implementation • ICLR 2021 • Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, Yan Xu
To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations.
Ranked #3 on Image Inpainting on FFHQ 512 x 512
no code implementations • 15 Nov 2020 • Peng Zhang, Yongchun Fang, Xiao Liang, He Lin, wei he
Due to the limitation of the drone's load capacity, various specific tasks need to be accomplished by multiple drones in collaboration.
Dynamical Systems Systems and Control Systems and Control
no code implementations • 28 Sep 2020 • Kareem Eltouny, Xiao Liang
In this study, a novel unsupervised learning approach for SHM is proposed.
no code implementations • 24 Sep 2020 • Xiao Liang, Seyed Omid Sajedi
It is shown that class variance correlates well with locations where the model makes mistakes.
no code implementations • 19 Apr 2020 • Cheng Feng, Xiao Liang, Daniel Schneegass, PengWei Tian
Therefore, in order to enhance the reliability of sensing applications, apart from the physical phenomena/processes of interest, we believe it is also highly important to monitor the reliability of sensors and clean the sensor data before analysis on them being conducted.
no code implementations • 16 Apr 2020 • Xiao Liang, Dan Nguyen, Steve Jiang
We trained a model on CBCT images acquired from one vendor's scanners for head and neck cancer patients and applied it to images from another vendor's scanners and for other disease sites.
no code implementations • 10 Apr 2020 • Seyed Omid Sajedi, Xiao Liang
This paper proposes Bayesian inference for deep vision SHM models where uncertainty can be quantified using the Monte Carlo dropout sampling.
no code implementations • 23 Oct 2019 • Seyed Omid Sajedi, Xiao Liang
This paper proposes a robust framework to build a damage prediction model for building structures.
no code implementations • SEMEVAL 2019 • Zhengwei Lv, Duoxing Liu, Haifeng Sun, Xiao Liang, Tao Lei, Zhizhong Shi, Feng Zhu, Lei Yang
In order to address this task, we propose a system based on the BERT model with meta information of questions.
no code implementations • 23 May 2019 • Seyed Omid Sajedi, Xiao Liang
In the last decade, camera-equipped unmanned aerial vehicles (UAVs) have been widely used for visual inspections; however, the task of automatically extracting useful information from raw images is still challenging.
no code implementations • 31 Oct 2018 • Xiao Liang, Liyuan Chen, Dan Nguyen, Zhiguo Zhou, Xuejun Gu, Ming Yang, Jing Wang, Steve Jiang
Dose calculation accuracy using sCT images has been improved over the original CBCT images, with the average Gamma Index passing rate increased from 95. 4% to 97. 4% for 1 mm/1% criteria.
Medical Physics
no code implementations • 30 Jan 2018 • Hongzhi Zhang, Guandong Xu, Xiao Liang, Tinglei Huang, Kun fu
Then, instead of merging the sequence into a single vector with pooling operation, soft alignments between words from the question and the relation are learned.
no code implementations • 21 Nov 2017 • Jiajia Guo, Hongwei Du, Bensheng Qiu, Xiao Liang
Relative location prediction in computed tomography (CT) scan images is a challenging problem.