Zobrazeno 1 - 10
of 3 354
pro vyhledávání: '"An, Ruibing"'
Autor:
Li, Zhuo, Luo, Mingshuang, Hou, Ruibing, Zhao, Xin, Liu, Hao, Chang, Hong, Liu, Zimo, Li, Chen
Human motion generation plays a vital role in applications such as digital humans and humanoid robot control. However, most existing approaches disregard physics constraints, leading to the frequent production of physically implausible motions with p
Externí odkaz:
http://arxiv.org/abs/2411.14951
Pre-trained vision-language models (e.g., CLIP) have shown powerful zero-shot transfer capabilities. But they still struggle with domain shifts and typically require labeled data to adapt to downstream tasks, which could be costly. In this work, we a
Externí odkaz:
http://arxiv.org/abs/2411.06921
Autor:
Li, Keliang, Yang, Zaifei, Zhao, Jiahe, Shen, Hongze, Hou, Ruibing, Chang, Hong, Shan, Shiguang, Chen, Xilin
The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centric scenarios. However, existin
Externí odkaz:
http://arxiv.org/abs/2410.06777
Autor:
Yu, Zhuonan, Qin, Peijun, Sun, Ruibing, Khademi, Sara, Xu, Zhen, Sun, Qinchao, Tai, Yanlong, Song, Bing, Guo, Tianruo, Wang, Hao
The myelinated axons are widely present in both central and peripheral nervous systems. Its unique compact spiraling structure poses significant challenges to understanding its biological functions and developmental mechanisms. Conventionally, myelin
Externí odkaz:
http://arxiv.org/abs/2409.16533
Limited by the scale and diversity of time series data, the neural networks trained on time series data often overfit and show unsatisfacotry performances. In comparison, large language models (LLMs) recently exhibit impressive generalization in dive
Externí odkaz:
http://arxiv.org/abs/2406.08765
Traditional semi-supervised learning (SSL) assumes that the feature distributions of labeled and unlabeled data are consistent which rarely holds in realistic scenarios. In this paper, we propose a novel SSL setting, where unlabeled samples are drawn
Externí odkaz:
http://arxiv.org/abs/2405.20596
Autor:
Luo, Mingshuang, Hou, Ruibing, Li, Zhuo, Chang, Hong, Liu, Zimo, Wang, Yaowei, Shan, Shiguang
This paper presents M$^3$GPT, an advanced $\textbf{M}$ultimodal, $\textbf{M}$ultitask framework for $\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representat
Externí odkaz:
http://arxiv.org/abs/2405.16273
Autor:
Zhao, Jiahe, Hou, Ruibing, Chang, Hong, Gu, Xinqian, Ma, Bingpeng, Shan, Shiguang, Chen, Xilin
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relevant features. However, we observe that relying solely on clothes-irrel
Externí odkaz:
http://arxiv.org/abs/2404.09507
Sourced from various sensors and organized chronologically, Multivariate Time-Series (MTS) data involves crucial spatial-temporal dependencies, e.g., correlations among sensors. To capture these dependencies, Graph Neural Networks (GNNs) have emerged
Externí odkaz:
http://arxiv.org/abs/2403.03645
Autor:
Guo, Jingcai, Zhou, Qihua, Li, Ruibing, Lu, Xiaocheng, Liu, Ziming, Chen, Junyang, Xie, Xin, Zhang, Jie
This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL), dubbed ParsNets, where we are interested in learning a composition of on-device friendly linear networks, each with orthogonality and low-rankness properties,
Externí odkaz:
http://arxiv.org/abs/2312.09709