no code implementations • 23 Apr 2024 • Hong Huang, Yuyi Wang, Luyao Li, Jun Lin
Previous studies on music style transfer have mainly focused on one-to-one style conversion, which is relatively limited.
no code implementations • 22 Feb 2024 • Miaoxin Wang, Xiao Wu, Jun Lin, Zhongfeng Wang
Particularly, it demonstrates efficient support for large-kernel CNNs, achieving throughputs of 169. 68 GOPS and 244. 55 GOPS for RepLKNet-31 and PyConvResNet-50, respectively, both of which are implemented on hardware for the first time.
no code implementations • 15 Sep 2023 • Longwei Huang, Chao Fang, Qiong Li, Jun Lin, Zhongfeng Wang
However, many edge devices struggle to boost inference throughput of various quantized DNNs due to the varying quantization levels, and these devices lack floating-point (FP) support for on-device learning, which prevents them from improving model accuracy while ensuring data privacy.
no code implementations • 19 Aug 2023 • Kaihang Pan, Juncheng Li, Wenjie Wang, Hao Fei, Hongye Song, Wei Ji, Jun Lin, Xiaozhong Liu, Tat-Seng Chua, Siliang Tang
Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks often entail distinct search intents.
1 code implementation • 23 May 2023 • Xiangnan Chen, Qian Xiao, Juncheng Li, Duo Dong, Jun Lin, Xiaozhong Liu, Siliang Tang
GOSE initiates by generating preliminary relation predictions on entity pairs extracted from a scanned image of the document.
no code implementations • 22 Mar 2023 • Kaihang Pan, Juncheng Li, Hongye Song, Jun Lin, Xiaozhong Liu, Siliang Tang
Though effective, prompt tuning under few-shot settings on the one hand heavily relies on a good initialization of soft prompts.
no code implementations • 16 Nov 2022 • Siyuan Lu, Chenchen Zhou, Keli Xie, Jun Lin, Zhongfeng Wang
Based on ELBERT, an innovative method to accelerate text processing on the GPU platform is developed, solving the difficult problem of making the early exit mechanism work more effectively with a large input batch size.
no code implementations • 18 Oct 2022 • Ziqi Su, Wendong Mao, Zhongfeng Wang, Jun Lin, WenQiang Wang, Haitao Sun
3D deconvolution (DeConv), as an important computation of 3D-GAN, significantly increases computational complexity compared with 2D DeConv.
no code implementations • 14 Oct 2022 • Zilun Wang, Wendong Mao, Peixiang Yang, Zhongfeng Wang, Jun Lin
The submanifold sparse convolutional network (SSCN) has been widely used for the point cloud due to its unique advantages in terms of visual results.
no code implementations • 12 Jul 2022 • Pere Izquierdo Gómez, Alberto Barragan Moreno, Jun Lin, Tomislav Dragičević
This paper proposes a human-interpretable data-driven method for anomaly detection in EV charging stations, aiming to provide information for the condition monitoring and predictive maintenance of power converters within such a station.
no code implementations • 29 Apr 2021 • Yongzhen Wang, Xiaozhong Liu, Katy Börner, Jun Lin, Yingnan Ju, Changlong Sun, Luo Si
Objective: Ubiquitous internet access is reshaping the way we live, but it is accompanied by unprecedented challenges in preventing chronic diseases that are usually planted by long exposure to unhealthy lifestyles.
1 code implementation • 14 Dec 2020 • Yicheng Zou, Jun Lin, Lujun Zhao, Yangyang Kang, Zhuoren Jiang, Changlong Sun, Qi Zhang, Xuanjing Huang, Xiaozhong Liu
Automatic chat summarization can help people quickly grasp important information from numerous chat messages.
1 code implementation • 14 Dec 2020 • Yicheng Zou, Lujun Zhao, Yangyang Kang, Jun Lin, Minlong Peng, Zhuoren Jiang, Changlong Sun, Qi Zhang, Xuanjing Huang, Xiaozhong Liu
In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics.
no code implementations • 24 Oct 2020 • Guiping Zhou, Guannan Gao, Jingxiu Wang, Jun Lin, Yingna Su, Chunlan Jin, Yuzong Zhang
By revisiting the successive eruptions on 2012 March 7, fast-mode shocks are identified to account for the X5. 4 flare-related EUV wave with a velocity of 550 km/s, and appeared faster than 2060$\pm$270 km/s at the front of the corresponding coronal mass ejection in the slow-rising phase.
Solar and Stellar Astrophysics
no code implementations • 18 Sep 2020 • Siyuan Lu, Meiqi Wang, Shuang Liang, Jun Lin, Zhongfeng Wang
Designing hardware accelerators for deep neural networks (DNNs) has been much desired.
no code implementations • IJCNLP 2019 • Kaisong Song, Lidong Bing, Wei Gao, Jun Lin, Lujun Zhao, Jiancheng Wang, Changlong Sun, Xiaozhong Liu, Qiong Zhang
Customers ask questions and customer service staffs answer their questions, which is the basic service model via multi-turn customer service (CS) dialogues on E-commerce platforms.
no code implementations • 6 Sep 2019 • Jinming Lu, Siyuan Lu, Zhisheng Wang, Chao Fang, Jun Lin, Zhongfeng Wang, Li Du
With the increasing size of Deep Neural Network (DNN) models, the high memory space requirements and computational complexity have become an obstacle for efficient DNN implementations.
no code implementations • 31 May 2019 • Haonan Wang, Jun Lin, Zhongfeng Wang
Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability.
no code implementations • 8 May 2019 • Siyuan Lu, Jinming Lu, Jun Lin, Zhongfeng Wang
Firstly, we improve the beam search decoding algorithm to save the storage space.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 4 Jul 2018 • Zhisheng Wang, Fangxuan Sun, Jun Lin, Zhongfeng Wang, Bo Yuan
Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper.
1 code implementation • 29 Nov 2017 • Qiong Wu, Fan Zhang, Hao Wang, Jun Lin, Yang Liu
The Alternating Direction Method of Multipliers (ADMM) decoding of Low Density Parity Check (LDPC) codes has received many attentions due to its excellent performance at the error floor region.
Information Theory Information Theory
no code implementations • 10 Jul 2016 • Fangxuan Sun, Jun Lin, Zhongfeng Wang
In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered.