Publications

SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation

Published in 2023 International Conference on Computer Vision (ICCV), 2023

Download paper here

Recommended citation: Zhang, Y., Chen, D., Kundu, S., Li, C., & Beerel, P. A. (2023). SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 5116-5125).

TLCD: A Transformer based Loop Closure Detection for Robotic Visual SLAM

Published in 2022 International Conference on Advanced Robotics and Mechatronics (ICARM), 2022

Download paper here

Recommended citation: Li, C., Ren, H., Bi, M., Ding, C., Li, W., Zhang, R., ... & Yu, H. (2022, July). TLCD: A Transformer based Loop Closure Detection for Robotic Visual SLAM. In 2022 International Conference on Advanced Robotics and Mechatronics (ICARM) (pp. 261-267). IEEE.

An edge-device based fast fall detection using spatio-temporal optical flow model

Published in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021

Download paper here

Recommended citation: Yang, Y., Ren, H., Li, C., Ding, C., & Yu, H. (2021, November). An edge-device based fast fall detection using spatio-temporal optical flow model. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 5067-5071). IEEE.

Atfvo: An attentive tensor-compressed lstm model with optical flow features for monocular visual odometry

Published in 2021 WRC Symposium on Advanced Robotics and Automation (WRC SARA), 2021

Download paper here

Recommended citation: Ren, H., Li, C., Zhang, X., Ding, C., Man, C., & Yu, H. (2021, September). Atfvo: An attentive tensor-compressed lstm model with optical flow features for monocular visual odometry. In 2021 WRC Symposium on Advanced Robotics and Automation (WRC SARA) (pp. 79-85). IEEE.