no code implementations • NAACL (SUKI) 2022 • Xiaofeng Chen, YiRong Chen, Xiaofen Xing, Xiangmin Xu, Wenjing Han, Qianfeng Tie
Because of the compositionality of natural language, syntactic structure which contains the information about the relationship between words is a key factor for semantic understanding.
1 code implementation • 1 Nov 2023 • YiRong Chen, Xiaofen Xing, Jingkai Lin, huimin zheng, Zhenyu Wang, Qi Liu, Xiangmin Xu
Large language models (LLMs) have been widely applied in various fields due to their excellent capability for memorizing knowledge and chain of thought (CoT).
1 code implementation • 24 Oct 2023 • YiRong Chen, Zhenyu Wang, Xiaofen Xing, huimin zheng, Zhipei Xu, Kai Fang, Junhong Wang, Sihang Li, Jieling Wu, Qi Liu, Xiangmin Xu
Large language models (LLMs) have performed well in providing general and extensive health suggestions in single-turn conversations, exemplified by systems such as ChatGPT, ChatGLM, ChatDoctor, DoctorGLM, and etc.
no code implementations • 23 Oct 2023 • Junpeng Tan, Chunmei Qing, Xiangmin Xu
By adding linear image domain error analysis, the noise is reduced after under-sampled and DFT processing, and the anti-interference ability of the algorithm is enhanced.
no code implementations • 17 Oct 2023 • Zhaojie Chu, Kailing Guo, Xiaofen Xing, Yilin Lan, Bolun Cai, Xiangmin Xu
In this study, we propose a novel framework, CorrTalk, which effectively establishes the temporal correlation between hierarchical speech features and facial activities of different intensities across distinct regions.
no code implementations • 16 Oct 2023 • Junpeng Tan, Xin Zhang, Yao Lv, Xiangmin Xu, Gang Li
Finally, the experimental results on real-world fetal brain MRI stacks demonstrate the state-of-the-art performance of our method.
no code implementations • 4 Oct 2023 • Kaijun Gong, Zhuowen Yin, Yushu Li, Kailing Guo, Xiangmin Xu
To reduce the data-dependent redundancy, we devise a dynamic shuffle module to generate data-dependent permutation matrices for shuffling.
no code implementations • 25 Sep 2023 • Pucheng Zhai, Kailing Guo, Fang Liu, Xiaofen Xing, Xiangmin Xu
Therefore the pruning strategy can gradually prune the network and automatically determine the appropriate pruning rates for each layer.
1 code implementation • 20 Jul 2023 • Weidong Chen, Xiaofen Xing, Peihao Chen, Xiangmin Xu
Although PTMs shed new light on artificial general intelligence, they are constructed with general tasks in mind, and thus, their efficacy for specific tasks can be further improved.
1 code implementation • 3 Mar 2023 • Shuaiqi Chen, Xiaofen Xing, Weibin Zhang, Weidong Chen, Xiangmin Xu
Self-attention mechanism is applied within windows for capturing temporal important information locally in a fine-grained way.
1 code implementation • 27 Feb 2023 • Weidong Chen, Xiaofen Xing, Xiangmin Xu, Jianxin Pang, Lan Du
Paralinguistic speech processing is important in addressing many issues, such as sentiment and neurocognitive disorder analyses.
Ranked #1 on
Speech Emotion Recognition
on LSSED
1 code implementation • 28 Nov 2022 • Jiahao Sun, Chunmei Qing, Junpeng Tan, Xiangmin Xu
The key step in this framework is a novel query decoder with transformers that can capture the instance information through the superpoint cross-attention mechanism and generate the superpoint masks of the instances.
Ranked #4 on
3D Instance Segmentation
on ScanNet(v2)
no code implementations • 6 Jul 2022 • Kan Wang, Changxing Ding, Jianxin Pang, Xiangmin Xu
In this work, we propose a novel Context Sensing Attention Network (CSA-Net), which improves both the frame feature extraction and temporal aggregation steps.
1 code implementation • 29 May 2022 • YiRong Chen, Weiquan Fan, Xiaofen Xing, Jianxin Pang, Minlie Huang, Wenjing Han, Qianfeng Tie, Xiangmin Xu
Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation.
Ranked #1 on
Emotion Recognition in Conversation
on CPED
1 code implementation • 12 Apr 2022 • Kailing Guo, Zhenquan Lin, Xiaofen Xing, Fang Liu, Xiangmin Xu
In this paper, we devise a new training method, low-rank projection with energy transfer (LRPET), that trains low-rank compressed networks from scratch and achieves competitive performance.
1 code implementation • 9 Oct 2021 • Zhenquan Lin, Kailing Guo, Xiaofen Xing, Xiangmin Xu
Comprehensive experiments show that WE outperforms the other reactivation methods and plug-in training methods with typical convolutional neural networks, especially lightweight networks.
no code implementations • 3 Mar 2021 • Tong Shen, Gyorgy Lur, Xiangmin Xu, Zhaoxia Yu
With the increasing popularity of calcium imaging data in neuroscience research, methods for analyzing calcium trace data are critical to address various questions.
1 code implementation • 30 Jan 2021 • Weiquan Fan, Xiangmin Xu, Xiaofen Xing, Weidong Chen, DongYan Huang
Speech emotion recognition is a vital contributor to the next generation of human-computer interaction (HCI).
Ranked #3 on
Speech Emotion Recognition
on LSSED
1 code implementation • 14 May 2019 • Weirui Lu, Xiaofen Xing, Bolun Cai, Xiangmin Xu
However, the performance of ranking-based methods is often poor and this is mainly due to two reasons: 1) image cropping is a listwise ranking task rather than pairwise comparison; 2) the rescaling caused by pooling layer and the deformation in view generation damage the performance of composition learning.
1 code implementation • 23 Apr 2019 • Bolun Cai, Xiangmin Xu, Xiaofen Xing, Kui Jia, Jie Miao, DaCheng Tao
Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion.
no code implementations • 27 Dec 2017 • Nitin Agarwal, Xiangmin Xu, Gopi Meenakshisundaram
In this paper we present techniques and algorithms for automatic registration and 3D reconstruction of conventionally produced mouse brain slices in a standardized atlas space.
no code implementations • 4 Dec 2017 • Bolun Cai, Xiangmin Xu, Kailing Guo, Kui Jia, DaCheng Tao
With the powerful down-sampling process, the co-training DSN set a new state-of-the-art performance for image super-resolution.
2 code implementations • 25 Jun 2017 • Suo Qiu, Xiangmin Xu, Bolun Cai
Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks.
no code implementations • 9 Jun 2017 • Jie Miao, Xiangmin Xu, Xiaofen Xing, DaCheng Tao
However, complex temporal variations require high-level semantic representations to fully achieve temporal slowness, and thus it is impractical to learn a high-level representation from dynamic textures directly by SFA.
no code implementations • 15 May 2017 • Xiaoyi Jia, Xiangmin Xu, Bolun Cai, Kailing Guo
However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which limits the flexibility of models to infer various scales of details for high resolution (HR) output.
1 code implementation • 8 Feb 2017 • Lingke Zeng, Xiangmin Xu, Bolun Cai, Suo Qiu, Tong Zhang
Crowd counting on static images is a challenging problem due to scale variations.
3 code implementations • 28 Jan 2016 • Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, DaCheng Tao
The key to achieve haze removal is to estimate a medium transmission map for an input hazy image.
Ranked #7 on
Image Dehazing
on RS-Haze