no code implementations • 25 Mar 2024 • Hannah Schieber, Shiyu Li, Niklas Corell, Philipp Beckerle, Julian Kreimeier, Daniel Roth
Existing work, combining object detection/6D pose estimation and assembly state detection focuses either on pure deep learning-based approaches, or limit the assembly state detection to building blocks.
1 code implementation • 12 Feb 2024 • Shiyu Li, Hannah Schieber, Niklas Corell, Bernhard Egger, Julian Kreimeier, Daniel Roth
Augmented reality assembly guidance requires 6D object poses of target objects in real time.
no code implementations • 5 Jan 2024 • Syed Hasib Akhter Faruqui, Adel Alaeddini, Yan Du, Shiyu Li, Kumar Sharma, Jing Wang
Participants were randomly assigned to an intervention (AI, n=10) group to receive daily AI-generated individualized feedback or a control group without receiving the daily feedback (non-AI, n=10) in the last three months.
1 code implementation • 14 Dec 2023 • Qijun Zhang, Shiyu Li, Guanglei Zhou, Jingyu Pan, Chen-Chia Chang, Yiran Chen, Zhiyao Xie
Based on the formulation, we propose PANDA, an innovative architecture-level solution that combines the advantages of analytical and ML power models.
no code implementations • 29 Oct 2023 • Zhixu Du, Shiyu Li, Yuhao Wu, Xiangyu Jiang, Jingwei Sun, Qilin Zheng, Yongkai Wu, Ang Li, Hai "Helen" Li, Yiran Chen
Specifically, SiDA attains a remarkable speedup in MoE inference with up to 3. 93X throughput increasing, up to 75% latency reduction, and up to 80% GPU memory saving with down to 1% performance drop.
1 code implementation • CVPR 2023 • Xuan Zhang, Shiyu Li, Xi Li, Ping Huang, Jiulong Shan, Ting Chen
In this study, we propose an improved model called DeSTSeg, which integrates a pre-trained teacher network, a denoising student encoder-decoder, and a segmentation network into one framework.
Ranked #35 on Anomaly Detection on MVTec AD
1 code implementation • 19 Nov 2021 • Shiyu Li, Hao Ma, Xiangyu Hu
This work focuses on image beauty assessment.