3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks

no code implementations • 15 Mar 2021 • Aniruddha Ganguly, Tasin Ishmam, Khandker Aftarul Islam, Md Zahidur Rahman, Md. Shamsuzzoha Bayzid

Compared to F-ConvNet, we achieve improvements in training and inference times by up to 62. 80% and 58. 96%, respectively, while reducing the memory usage by up to 58. 53%.

3D Object Detection Autonomous Vehicles +3

Align-gram : Rethinking the Skip-gram Model for Protein Sequence Analysis

1 code implementation • 6 Dec 2020 • Nabil Ibtehaz, S. M. Shakhawat Hossain Sourav, Md. Shamsuzzoha Bayzid, M. Sohel Rahman

Background: The inception of next generations sequencing technologies have exponentially increased the volume of biological sequence data.