3.4k citations · 3.7k across the 22 of their papers we have counts for
22 papers
Multi-Scale Temporal Transformer For Speech Emotion Recognition
Zhipeng Li, Xiaofen Xing, Yuanbo Fang +3
Speech emotion recognition plays a crucial role in human-machine interaction systems. Recently various optimized Transformers have been successfully applied to speech emotion recog…
LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch
Pucheng Zhai, Kailing Guo, Fang Liu +2
Structured pruning is a commonly used convolutional neural network (CNN) compression approach. Pruning rate setting is a fundamental problem in structured pruning. Most existing wo…
Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition
Weidong Chen, Xiaofen Xing, Peihao Chen +1
This paper presents a paradigm that adapts general large-scale pretrained models (PTMs) to speech emotion recognition task. Although PTMs shed new light on artificial general intel…
DWFormer: Dynamic Window transFormer for Speech Emotion Recognition
Shuaiqi Chen, Xiaofen Xing, Weibin Zhang +2
Speech emotion recognition is crucial to human-computer interaction. The temporal regions that represent different emotions scatter in different parts of the speech locally. Moreov…
SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing
Weidong Chen, Xiaofen Xing, Xiangmin Xu +2
Paralinguistic speech processing is important in addressing many issues, such as sentiment and neurocognitive disorder analyses. Recently, Transformer has achieved remarkable succe…
DST: Deformable Speech Transformer for Emotion Recognition
Weidong Chen, Xiaofen Xing, Xiangmin Xu +2
Enabled by multi-head self-attention, Transformer has exhibited remarkable results in speech emotion recognition (SER). Compared to the original full attention mechanism, window-ba…
Superpoint Transformer for 3D Scene Instance Segmentation
Jiahao Sun, Chunmei Qing, Junpeng Tan +1
Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward method…
Context Sensing Attention Network for Video-based Person Re-identification
Kan Wang, Changxing Ding, Jianxin Pang +1
Video-based person re-identification (ReID) is challenging due to the presence of various interferences in video frames. Recent approaches handle this problem using temporal aggreg…
CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
Yirong Chen, Weiquan Fan, Xiaofen Xing +5
Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers' personalities and emotions aft…
Compact Model Training by Low-Rank Projection with Energy Transfer
Kailing Guo, Zhenquan Lin, Canyang Chen +3
Low-rankness plays an important role in traditional machine learning, but is not so popular in deep learning. Most previous low-rank network compression methods compress networks b…
SpeechFormer: A Hierarchical Efficient Framework Incorporating the Characteristics of Speech
Weidong Chen, Xiaofen Xing, Xiangmin Xu +2
Transformer has obtained promising results on cognitive speech signal processing field, which is of interest in various applications ranging from emotion to neurocognitive disorder…
Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values
Zhenquan Lin, Kailing Guo, Xiaofen Xing +1
To obtain good performance, convolutional neural networks are usually over-parameterized. This phenomenon has stimulated two interesting topics: pruning the unimportant weights for…
Key-Sparse Transformer for Multimodal Speech Emotion Recognition
Weidong Chen, Xiaofeng Xing, Xiangmin Xu +2
Speech emotion recognition is a challenging research topic that plays a critical role in human-computer interaction. Multimodal inputs further improve the performance as more emoti…
LSSED: a large-scale dataset and benchmark for speech emotion recognition
Weiquan Fan, Xiangmin Xu, Xiaofen Xing +2
Speech emotion recognition is a vital contributor to the next generation of human-computer interaction (HCI). However, current existing small-scale databases have limited the devel…
Listwise View Ranking for Image Cropping
Weirui Lu, Xiaofen Xing, Bolun Cai +1
Rank-based Learning with deep neural network has been widely used for image cropping. However, the performance of ranking-based methods is often poor and this is mainly due to two…
BIT: Biologically Inspired Tracker
Bolun Cai, Xiangmin Xu, Xiaofen Xing +3
Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion. Given the superior tr…
Deep Sampling Networks
Bolun Cai, Xiangmin Xu, Kailing Guo +2
Deep convolutional neural networks achieve excellent image up-sampling performance. However, CNN-based methods tend to restore high-resolution results highly depending on tradition…
Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition
Jie Miao, Xiangmin Xu, Xiaofen Xing +1
Dynamic textures exist in various forms, e.g., fire, smoke, and traffic jams, but recognizing dynamic texture is challenging due to the complex temporal variations. In this paper,…
Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network
Xiaoyi Jia, Xiangmin Xu, Bolun Cai +1
Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images…
Multi-scale Convolutional Neural Networks for Crowd Counting
Lingke Zeng, Xiangmin Xu, Bolun Cai +2
Crowd counting on static images is a challenging problem due to scale variations. Recently deep neural networks have been shown to be effective in this task. However, existing neur…
Improving training of deep neural networks via Singular Value Bounding
Kui Jia
Deep learning methods achieve great success recently on many computer vision problems, with image classification and object detection as the prominent examples. In spite of these p…
DehazeNet: An End-to-End System for Single Image Haze Removal
Bolun Cai, Xiangmin Xu, Kui Jia +2
Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal i…