IEEE

Visual Kinematics Representation via Self-Supervised Object Tracking for Deep Reinforcement Learning

Abstract: Feature representation is critical for deep reinforcement learning (RL) in terms of sample efficiency and asymptotic performance. Previously developed feature representation methods in deep ...
GitHub

Efficient Visual Representation Learning with Bidirectional State Space Model

May. 2nd, 2024: Vision Mamba (Vim) is accepted by ICML2024. 🎉 Conference page can be found here. Feb. 10th, 2024: We update Vim-tiny/small weights and training scripts. By placing the class token at ...
Scientific Research Publishing

Pain, J.-C. (2024) Integral Representations of the Riemann Zeta Function of Odd Argument. arXiv:2410.23096.

ABSTRACT: The Riemann Zeta function ζ( s ) has many different representations. In this paper, we derive several new integral representations of the Zeta function using the inverse Mellin transform and ...
IEEE

VDNA-PR: Using General Dataset Representations for Robust Sequential Visual Place Recognition

Abstract: This paper adapts a general dataset representation technique to produce robust Visual Place Recognition (VPR) descriptors, crucial to enable real-world mobile robot localisation. Two ...