Linked Dynamic Graph CNN: Learning through Point Cloud by Linking Hierarchical Features - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Kuangen Zhang, Ming Hao, Jing Wang, Xinxing Chen, Yuquan Leng, Clarence W. de Silva, Chenglong Fu 0001. Linked Dynamic Graph CNN: Learning through Point Cloud by Linking Hierarchical Features. In 27th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2021, Shanghai, China, November 26-28, 2021. pages 7-12, IEEE, 2021. [doi]

The following publications are possibly variants of this publication:

Dynamic Graph CNN for Learning on Point CloudsYue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon. tog, 38(5), 2019. [doi]

How good are machine learning clouds for binary classification with good features?: extended abstractHantian Zhang, Luyuan Zeng, Wentao Wu 0001, Ce Zhang. CLOUD 2017: 649 [doi]

Linked Attention-Based Dynamic Graph Convolution Module for Point Cloud ClassificationXiaolong Lu, Baodi Liu, Weifeng Liu, Kai Zhang, Ye Li, Xiaoping Lu. icip 2021: 3153-3157 [doi]

Dynamic and Decentralized Global Analytics via Machine LearningHao Wang, Di Niu, Baochun Li. CLOUD 2018: 14-25 [doi]

Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic QuantizationAmey Agrawal, Sameer Reddy, Satwik Bhattamishra, Venkata Prabhakara Sarath Nookala, Vidushi Vashishth, Kexin Rong 0001, Alexey Tumanov. CLOUD 2024: 1012-1031 [doi]

Semi-dynamic load balancing: efficient distributed learning in non-dedicated environmentsChen Chen 0015, Qizhen Weng, Wei Wang 0030, Baochun Li, Bo Li 0001. CLOUD 2020: 431-446 [doi]

runs on WebDSL