no code implementations • NAACL (SUKI) 2022 • Lingbo Mo, Zhen Wang, Jie Zhao, Huan Sun
More fine-grained analyses on transfer behaviors reveal the types of transferred knowledge and transfer patterns.
no code implementations • COLING 2022 • Jason Ingyu Choi, Saar Kuzi, Nikhita Vedula, Jie Zhao, Giuseppe Castellucci, Marcus Collins, Shervin Malmasi, Oleg Rokhlenko, Eugene Agichtein
Conversational Task Assistants (CTAs) are conversational agents whose goal is to help humans perform real-world tasks.
no code implementations • 8 Apr 2024 • Qinglu Min, Jie Zhao, Zhihao Zhang, Chen Min
Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS).
no code implementations • 26 Mar 2024 • Yingtao Shen, Minqing Sun, Jie Zhao, An Zou
Convolutional neural networks (CNNs) have achieved significant popularity, but their computational and memory intensity poses challenges for resource-constrained computing systems, particularly with the prerequisite of real-time performance.
no code implementations • 28 Feb 2024 • Xiaosong Wang, Xiaofan Zhang, Guotai Wang, Junjun He, Zhongyu Li, Wentao Zhu, Yi Guo, Qi Dou, Xiaoxiao Li, Dequan Wang, Liang Hong, Qicheng Lao, Tong Ruan, Yukun Zhou, Yixue Li, Jie Zhao, Kang Li, Xin Sun, Lifeng Zhu, Shaoting Zhang
The emerging trend of advancing generalist artificial intelligence, such as GPTv4 and Gemini, has reshaped the landscape of research (academia and industry) in machine learning and many other research areas.
no code implementations • 13 Feb 2024 • Maurice Diesendruck, Jianzhe Lin, Shima Imani, Gayathri Mahalingam, Mingyang Xu, Jie Zhao
When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion.
no code implementations • 14 Jan 2024 • Xiao Liu, Jie Zhao, Wubing Chen, Mao Tan, Yongxing Su
To address this issue, we propose a novel self-interpretable structure, named Backbone Extract Tree (BET), to better explain the agent's behavior by identify the error-prone states.
1 code implementation • 3 Nov 2023 • Mingze Yuan, Peng Bao, Jiajia Yuan, Yunhao Shen, ZiFan Chen, Yi Xie, Jie Zhao, Yang Chen, Li Zhang, Lin Shen, Bin Dong
This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support.
1 code implementation • 4 Oct 2023 • Murong Yue, Jie Zhao, Min Zhang, Liang Du, Ziyu Yao
Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services.
no code implementations • 29 Sep 2023 • Jie Zhao, Ziyu Guan, Wei Zhao, Yue Jiang, Xiaofei He
Recent works considering professional legal-linguistic style (PLLS) texts have shown promising results on the charge prediction task.
no code implementations • 15 Sep 2023 • Jie Zhao, Johan Edstedt, Michael Felsberg, Dong Wang, Huchuan Lu
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance.
no code implementations • 26 Jul 2023 • Hong Lu, Chuan Li, Yinheng Li, Jie Zhao
The drug development process necessitates that pharmacologists undertake various tasks, such as reviewing literature, formulating hypotheses, designing experiments, and interpreting results.
no code implementations • 29 Jun 2023 • Arvi Jonnarth, Jie Zhao, Michael Felsberg
Coverage path planning (CPP) is the problem of finding a path that covers the entire free space of a confined area, with applications ranging from robotic lawn mowing to search-and-rescue.
1 code implementation • 16 Jun 2023 • Dequan Wang, Xiaosong Wang, Lilong Wang, Mengzhang Li, Qian Da, Xiaoqiang Liu, Xiangyu Gao, Jun Shen, Junjun He, Tian Shen, Qi Duan, Jie Zhao, Kang Li, Yu Qiao, Shaoting Zhang
Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications.
no code implementations • 29 May 2023 • ZiFan Chen, Jiazheng Li, Jie Zhao, Yiting Liu, Hongfeng Li, Bin Dong, Lei Tang, Li Zhang
This model consists of a proposing stage for coarse segmentation and a refining stage for improved segmentation, using two-way branches for enhanced performance and an up-down strategy for efficiency.
no code implementations • 23 May 2023 • Ruiqi Sun, Siwei Ye, Jie Zhao, Xin He, Yiran Li, An Zou
The inherent diversity of computation types within individual Deep Neural Network (DNN) models imposes a corresponding need for a varied set of computation units within hardware processors.
no code implementations • 8 Mar 2023 • Silin Gao, Zhe Zhang, Muhan Wang, Yan Zhang, Jie Zhao, Bingchen Zhang, Yue Wang, Yirong Wu
This paper focuses on the gridless direction-of-arrival (DoA) estimation for data acquired by non-uniform linear arrays (NLAs) in automotive applications.
no code implementations • 27 Oct 2022 • Zhiyu Chen, Jie Zhao, Anjie Fang, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi
Furthermore, human evaluation shows that our method can generate more accurate and detailed rewrites when compared to human annotations.
1 code implementation • 22 May 2022 • Jie Zhao, Jingshu Zhang, Dongdong Li, Dong Wang
It contains a detection dataset with a total of 10, 000 images and a tracking dataset with 20 videos that include short-term and long-term sequences.
1 code implementation • 17 May 2022 • Hexin Dong, ZiFan Chen, Mingze Yuan, Yutong Xie, Jie Zhao, Fei Yu, Bin Dong, Li Zhang
Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning.
no code implementations • 19 Apr 2022 • Wei Chen, Jie Zhao, Wan-Lei Zhao, Song-Yuan Wu
In this paper, a single-stage monocular 3D object detection model is proposed.
1 code implementation • CVPR 2022 • Pengyu Zhang, Jie Zhao, Dong Wang, Huchuan Lu, Xiang Ruan
With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information.
Ranked #4 on Rgb-T Tracking on GTOT
1 code implementation • 16 Mar 2022 • ZiFan Chen, Jie Zhao, Hao Yu, Yue Zhang, Li Zhang
Accurate and efficient lumbar spine disease identification is crucial for clinical diagnosis.
no code implementations • 10 Mar 2022 • Gao-Dong Liu, Wan-Lei Zhao, Jie Zhao
Existing solutions either retrain the model from scratch or require the replay of old samples during the training.
no code implementations • 2 Mar 2022 • Boyang Ti, Yongsheng Gao, Jie Zhao, Sylvain Calinon
Daily manipulation tasks are characterized by geometric primitives related to actions and object shapes.
no code implementations • 13 Jan 2022 • Chunyuan Zhang, Chao Liu, Qi Song, Jie Zhao
However, limited by the strong correlation among sequential samples of the agent, ESN-based policy control algorithms are difficult to use the recursive least squares (RLS) algorithm to update the ESN's parameters.
1 code implementation • 28 Oct 2021 • Jinhui Yuan, Xinqi Li, Cheng Cheng, Juncheng Liu, Ran Guo, Shenghang Cai, Chi Yao, Fei Yang, Xiaodong Yi, Chuan Wu, Haoran Zhang, Jie Zhao
Aiming at a simple, neat redesign of distributed deep learning frameworks for various parallelism paradigms, we present OneFlow, a novel distributed training framework based on an SBP (split, broadcast and partial-value) abstraction and the actor model.
no code implementations • 29 Sep 2021 • Hexin Dong, Fei Yu, Jie Zhao, Bin Dong, Li Zhang
This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training.
no code implementations • 25 Sep 2021 • Zhili Li, Xuejin Chen, Jie Zhao, Zhiwei Xiong
However, due to the image degradation during the imaging process, the large variety of mitochondrial structures, as well as the presence of noise, artifacts and other sub-cellular structures, mitochondria segmentation is very challenging.
1 code implementation • ICCV 2021 • Kenan Dai, Jie Zhao, Lijun Wang, Dong Wang, Jianhua Li, Huchuan Lu, Xuesheng Qian, Xiaoyun Yang
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve.
1 code implementation • Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation 2021 • Jie Zhao, Bojie Li, Wang Nie, Zhen Geng, Renwei Zhang, Xiong Gao, Bin Cheng, Chen Wu, Yun Cheng, Zheng Li, Peng Di, Kun Zhang, Xuefeng Jin
Existing tensor compilers have proven their effectiveness in deploying deep neural networks on general-purpose hardware like CPU and GPU, but optimizing for neural processing units (NPUs) is still challenging due to the heterogeneous compute units and complicated memory hierarchy.
no code implementations • 8 Apr 2021 • Mo Zhang, Fei Yu, Jie Zhao, Li Zhang, Quanzheng Li
Blood vessel segmentation is crucial for many diagnostic and research applications.
no code implementations • 26 Feb 2021 • Jie Zhao, Xinghua Zhu, Jianzong Wang, Jing Xiao
In this paper an efficient method is proposed to evaluate the contributions of federated participants.
no code implementations • 24 Feb 2021 • Jie Zhao, Longhao Wu, Tiefu Li, Yu-xi Liu, Franco Nori, Yulong Liu, Jiangfeng Du
We study the phase controlled transmission properties in a compound system consisting of a 3D copper cavity and an yttrium iron garnet (YIG) sphere.
Quantum Physics Applied Physics Optics
no code implementations • 29 Jan 2021 • Zhichao Fang, Jie Zhao, Hong Li, Yang Liu
In this paper, the time fractional reaction-diffusion equations with the Caputo fractional derivative are solved by using the classical $L1$-formula and the finite volume element (FVE) methods on triangular grids.
Numerical Analysis Numerical Analysis 65N30, 65M60, 26A33 G.1.2; G.1.8
1 code implementation • 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) 2020 • Jie Zhao, Peng Di
Optimizing compilers exploit the memory hierarchy using loop tiling and fusion, but these two transformations usually interfere with each other due to the oversight of transformations on data in memories.
no code implementations • 11 Nov 2020 • Hongfeng Li, Yini Pan, Jie Zhao, Li Zhang
As an important part of this article, we then review the literature involving deep learning methods for skin disease diagnosis from several aspects according to the specific tasks.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Jie Zhao, Huan Sun
Code retrieval is a key task aiming to match natural and programming languages.
no code implementations • 4 Jul 2020 • Pengyu Zhang, Jie Zhao, Dong Wang, Huchuan Lu, Xiaoyun Yang
In this study, we propose a novel RGB-T tracking framework by jointly modeling both appearance and motion cues.
Ranked #6 on Rgb-T Tracking on GTOT
no code implementations • 5 Dec 2019 • Jie Zhao, Xiang Deng, Huan Sun
This paper makes one of the first efforts toward automatically generating complex questions from knowledge graphs.
no code implementations • 22 Nov 2019 • Jiankai Sun, Jie Zhao, Huan Sun, Srinivasan Parthasarathy
Routing newly posted questions (a. k. a cold questions) to potential answerers with the suitable expertise in Community Question Answering sites (CQAs) is an important and challenging task.
1 code implementation • 4 Nov 2019 • Jie Zhao, Lei Dai, Mo Zhang, Fei Yu, Meng Li, Hongfeng Li, Wenjia Wang, Li Zhang
The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.
no code implementations • 19 Sep 2019 • Jie Zhao, Xin Jiang, Xiaoman Wang, Shengfan Wang, Yun-hui Liu
The proposal in this paper is verified by a simulated assembly in which a robot arm completed the assembly process including parts picking from bin and a subsequent peg-in-hole assembly.
no code implementations • 26 Jul 2019 • Fei Yu, Jie Zhao, Yanjun Gong, Zhi Wang, Yuxi Li, Fan Yang, Bin Dong, Quanzheng Li, Li Zhang
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.
no code implementations • 7 Jul 2019 • Mo Zhang, Jie Zhao, Xiang Li, Li Zhang, Quanzheng Li
Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale.
2 code implementations • 19 Apr 2019 • Wenjia Wang, Junxuan Chen, Jie Zhao, Ying Chi, Xuansong Xie, Li Zhang, Xian-Sheng Hua
The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.
no code implementations • 24 Feb 2019 • Shengfan Wang, Xin Jiang, Jie Zhao, Xiaoman Wang, Weiguo Zhou, Yun-hui Liu, Fellow IEEE
This paper presents an efficient neural network model to generate robotic grasps with high resolution images.
Robotics
1 code implementation • 3 Dec 2018 • Jie Zhao, Quanzheng Li, Xiang Li, Hongfeng Li, Li Zhang
Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image.
no code implementations • EMNLP 2017 • Jie Zhao, Yu Su, Ziyu Guan, Huan Sun
Given a question and a set of answer candidates, answer triggering determines whether the candidate set contains any correct answers.