no code implementations • 21 May 2024 • Fan Shi, Chong Zhang, Takahiro Miki, Joonho Lee, Marco Hutter, Stelian Coros
Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL).
no code implementations • 18 Jan 2024 • Fan Shi, Bin Li, xiangyang xue
In the odd-one-out task and two held-out configurations, RAISE can leverage acquired latent concepts and atomic rules to find the rule-breaking image in a matrix and handle problems with unseen combinations of rules and attributes.
no code implementations • 27 Dec 2023 • Fan Shi
In this research, we introduce RefineNet, a novel architecture designed to address resolution limitations in text-to-image conversion systems.
1 code implementation • 15 Jul 2023 • Fan Shi, Bin Li, xiangyang xue
Finally, we conduct experiments to illustrate the interpretability of CRAB in concept learning, answer selection, and global rule abstraction.
no code implementations • 7 Apr 2023 • Yifan Yin, Xu Cheng, Fan Shi, Xiufeng Liu, Huan Huo, ShengYong Chen
Accurate and reliable optical remote sensing image-based small-ship detection is crucial for maritime surveillance systems, but existing methods often struggle with balancing detection performance and computational complexity.
1 code implementation • 15 Sep 2022 • Fan Shi, Bin Li, xiangyang xue
The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks.
no code implementations • 26 Oct 2021 • Tong Shen, Jiawei Zuo, Fan Shi, Jin Zhang, Liqin Jiang, Meng Chen, Zhengchen Zhang, Wei zhang, Xiaodong He, Tao Mei
We demonstrate ViDA-MAN, a digital-human agent for multi-modal interaction, which offers realtime audio-visual responses to instant speech inquiries.
2 code implementations • 22 Mar 2021 • Fan Shi, Bin Li, xiangyang xue
In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables.