354 citations · 517 across the 21 of their papers we have counts for
21 papers
Emotion-Conditioned Melody Harmonization with Hierarchical Variational Autoencoder
Shulei Ji, Xinyu Yang
Existing melody harmonization models have made great progress in improving the quality of generated harmonies, but most of them ignored the emotions beneath the music. Meanwhile, t…
How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning
Hang Chen, Jing Luo, Xinyu Yang +1
Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language mo…
Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning
Zhaoxi Mu, Xinyu Yang, Wenjing Zhu
Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information o…
Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance Segmentation
Chengxi Zeng, Xinyu Yang, David Smithard +3
This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medic…
Improving Domain Generalization with Domain Relations
Huaxiu Yao, Xinyu Yang, Xinyi Pan +3
Distribution shift presents a significant challenge in machine learning, where models often underperform during the test stage when faced with a different distribution than the one…
Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Xinyu Yang, Huaxiu Yao, Allan Zhou +1
There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. Current methods for addressing this problem only consider scenarios where all…
A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms
Hang Chen, Keqing Du, Xinyu Yang +1
Understanding causality helps to structure interventions to achieve specific goals and enables predictions under interventions. With the growing importance of learning causal relat…
Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction
Hang Chen, Xinyu Yang, Xiang Li
Emotion-cause pair extraction (ECPE) is an emerging task aiming to extract potential pairs of emotions and corresponding causes from documents. Previous approaches have focused on…
Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
Chengxi Zeng, Xinyu Yang, Majid Mirmehdi +2
We propose Video-TransUNet, a deep architecture for instance segmentation in medical CT videos constructed by integrating temporal feature blending into the TransUNet deep learning…
Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour
Feixiang Zhou, Xinyu Yang, Fang Chen +7
Automated social behaviour analysis of mice has become an increasingly popular research area in behavioural neuroscience. Recently, pose information (i.e., locations of keypoints o…
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Zhijian Liu, Haotian Tang, Alexander Amini +4
Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with ca…
Dynamic Curriculum Learning for Great Ape Detection in the Wild
Xinyu Yang, Tilo Burghardt, Majid Mirmehdi
We propose a novel end-to-end curriculum learning approach for sparsely labelled animal datasets leveraging large volumes of unlabelled data to improve supervised species detectors…
ADFF: Attention Based Deep Feature Fusion Approach for Music Emotion Recognition
Zi Huang, Shulei Ji, Zhilan Hu +3
Music emotion recognition (MER), a sub-task of music information retrieval (MIR), has developed rapidly in recent years. However, the learning of affect-salient features remains a…
DTWSSE: Data Augmentation with a Siamese Encoder for Time Series
Xinyu Yang, Xinlan Zhang, Zhenguo Zhang +2
Access to labeled time series data is often limited in the real world, which constrains the performance of deep learning models in the field of time series analysis. Data augmentat…
Review of end-to-end speech synthesis technology based on deep learning
Zhaoxi Mu, Xinyu Yang, Yizhuo Dong
As an indispensable part of modern human-computer interaction system, speech synthesis technology helps users get the output of intelligent machine more easily and intuitively, thu…
WakaVT: A Sequential Variational Transformer for Waka Generation
Yuka Takeishi, Mingxuan Niu, Jing Luo +2
Poetry generation has long been a challenge for artificial intelligence. In the scope of Japanese poetry generation, many researchers have paid attention to Haiku generation, but f…
A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
Shulei Ji, Jing Luo, Xinyu Yang
The utilization of deep learning techniques in generating various contents (such as image, text, etc.) has become a trend. Especially music, the topic of this paper, has attracted…
Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation Learning
Xinyu Yang, Majid Mirmehdi, Tilo Burghardt
In this paper we show that learning video feature spaces in which temporal cycles are maximally predictable benefits action classification. In particular, we propose a novel learni…
MG-VAE: Deep Chinese Folk Songs Generation with Specific Regional Style
Jing Luo, Xinyu Yang, Shulei Ji +1
Regional style in Chinese folk songs is a rich treasure that can be used for ethnic music creation and folk culture research. In this paper, we propose MG-VAE, a music generative m…
Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture
Andrey Kormilitzin, Xinyu Yang, William H. Stone +5
Understanding the morphological changes of primary neuronal cells induced by chemical compounds is essential for drug discovery. Using the data from a single high-throughput imagin…
Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending
Xinyu Yang, Majid Mirmehdi, Tilo Burghardt
We propose the first multi-frame video object detection framework trained to detect great apes. It is applicable to challenging camera trap footage in complex jungle environments a…