Outputs (5)

Wearable-based behaviour interpolation for semi-supervised human activity recognition (2024)
Journal Article
Duan, H., Wang, S., Ojha, V., Wang, S., Huang, Y., Long, Y., …Zheng, Y. (2024). Wearable-based behaviour interpolation for semi-supervised human activity recognition. Information Sciences, 665, Article 120393. https://doi.org/10.1016/j.ins.2024.120393

While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-and-error process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most deep learnin... Read More about Wearable-based behaviour interpolation for semi-supervised human activity recognition.

MRL-Seg: Overcoming Imbalance in Medical Image Segmentation With Multi-Step Reinforcement Learning (2023)
Journal Article
Yang, F., Li, X., Duan, H., Xu, F., Huang, Y., Zhang, X., …Zheng, Y. (2024). MRL-Seg: Overcoming Imbalance in Medical Image Segmentation With Multi-Step Reinforcement Learning. IEEE Journal of Biomedical and Health Informatics, 28(2), 858-869. https://doi.org/10.1109/jbhi.2023.3336726

Medical image segmentation is a critical task for clinical diagnosis and research. However, dealing with highly imbalanced data remains a significant challenge in this domain, where the region of interest (ROI) may exhibit substantial variations acro... Read More about MRL-Seg: Overcoming Imbalance in Medical Image Segmentation With Multi-Step Reinforcement Learning.

DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume (2023)
Journal Article
Miao, X., Bai, Y., Duan, H., Huang, Y., Wan, F., Xu, X., …Zheng, Y. (2023). DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume. IEEE Transactions on Circuits and Systems for Video Technology, https://doi.org/10.1109/tcsvt.2023.3305776

Self-supervised monocular depth estimation methods typically rely on the reprojection error to capture geometric relationships between successive frames in static environments. However, this assumption does not hold in dynamic objects in scenarios, l... Read More about DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume.

Dynamic Unary Convolution in Transformers (2023)
Journal Article
Duan, H., Long, Y., Wang, S., Zhang, H., Willcocks, C. G., & Shao, L. (2023). Dynamic Unary Convolution in Transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 12747 - 12759. https://doi.org/10.1109/tpami.2022.3233482

It is uncertain whether the power of transformer architectures can complement existing convolutional neural networks. A few recent attempts have combined convolution with transformer design through a range of structures in series, where the main cont... Read More about Dynamic Unary Convolution in Transformers.

EfficientTDNN: Efficient Architecture Search for Speaker Recognition (2022)
Journal Article
Wang, R., Wei, Z., Duan, H., Ji, S., Long, Y., & Hong, Z. (2022). EfficientTDNN: Efficient Architecture Search for Speaker Recognition. IEEE/ACM Transactions on Audio, Speech and Language Processing, 30, 2267-2279. https://doi.org/10.1109/taslp.2022.3182856

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing, and memory.... Read More about EfficientTDNN: Efficient Architecture Search for Speaker Recognition.