Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Yin, Jianxiong"'
With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensory inputs will be highly beneficial. Although several methods have been proposed to address different morphologies, it remains a challenge f
Externí odkaz:
http://arxiv.org/abs/2409.03332
Extracting and using class-discriminative features is critical for fine-grained recognition. Existing works have demonstrated the possibility of applying deep CNNs to exploit features that distinguish similar classes. However, CNNs suffer from proble
Externí odkaz:
http://arxiv.org/abs/2308.05396
Autor:
Zhou, Zhehua, Song, Jiayang, Xie, Xuan, Shu, Zhan, Ma, Lei, Liu, Dikai, Yin, Jianxiong, See, Simon
As a representative cyber-physical system (CPS), robotic manipulator has been widely adopted in various academic research and industrial processes, indicating its potential to act as a universal interface between the cyber and the physical worlds. Re
Externí odkaz:
http://arxiv.org/abs/2308.00055
Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples that could co
Externí odkaz:
http://arxiv.org/abs/2306.08306
Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training. To alleviate the catastrophic forgetting issue in CSS, a memory buffer that stores a small number of samples from the pr
Externí odkaz:
http://arxiv.org/abs/2304.05015
Autor:
Zhang, Huaizheng, Li, Yuanming, Xiao, Wencong, Huang, Yizheng, Di, Xing, Yin, Jianxiong, See, Simon, Luo, Yong, Lau, Chiew Tong, You, Yang
New architecture GPUs like A100 are now equipped with multi-instance GPU (MIG) technology, which allows the GPU to be partitioned into multiple small, isolated instances. This technology provides more flexibility for users to support both deep learni
Externí odkaz:
http://arxiv.org/abs/2301.00407
Modern quadrupeds are skillful in traversing or even sprinting on uneven terrains in a remote uncontrolled environment. However, survival in the wild requires not only maneuverability, but also the ability to handle potential critical hardware failur
Externí odkaz:
http://arxiv.org/abs/2210.00474
Autor:
Xu, Yuecong, Yang, Jianfei, Cao, Haozhi, Yin, Jianxiong, Chen, Zhenghua, Li, Xiaoli, Li, Zhengguo, Xu, Qianwen
While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to challenging environments in real-world scenarios are still under-explored
Externí odkaz:
http://arxiv.org/abs/2202.09545
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on their compre
Externí odkaz:
http://arxiv.org/abs/2109.12493
Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research towards video DA. This is partly due t
Externí odkaz:
http://arxiv.org/abs/2107.04932