Zobrazeno 1 - 10
of 936
pro vyhledávání: '"Zhao, Wentao"'
Although LiDAR semantic segmentation advances rapidly, state-of-the-art methods often incorporate specifically designed inductive bias derived from benchmarks originating from mechanical spinning LiDAR. This can limit model generalizability to other
Externí odkaz:
http://arxiv.org/abs/2407.11569
Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. By synthesizing samples through the interpolation of features and labels, Mixup effectively addresses the issue of data scarcity.
Externí odkaz:
http://arxiv.org/abs/2407.10681
Although Model Predictive Control (MPC) can effectively predict the future states of a system and thus is widely used in robotic manipulation tasks, it does not have the capability of environmental perception, leading to the failure in some complex s
Externí odkaz:
http://arxiv.org/abs/2407.09829
Robust and imperceptible adversarial video attack is challenging due to the spatial and temporal characteristics of videos. The existing video adversarial attack methods mainly take a gradient-based approach and generate adversarial videos with notic
Externí odkaz:
http://arxiv.org/abs/2406.01894
Autor:
Liu, Zhifen, Qiao, Dan, Xu, Yifan, Zhao, Wentao, Yang, Yang, Wen, Dan, Li, Xinrong, Nie, Xiaoping, Dong, Yongkang, Tang, Shiyou, Jiang, Yi, Wang, Ying, Zhao, Juan, Xu, Yong
Publikováno v:
Journal of Medical Internet Research, Vol 23, Iss 5, p e26883 (2021)
BackgroundThe prevalence of depressive and anxiety symptoms in patients with COVID-19 is higher than usual. Previous studies have shown that there are drug-to-drug interactions between antiretroviral drugs and antidepressants. Therefore, an effective
Externí odkaz:
https://doaj.org/article/da896905ed664399b3a8d3099f23e6c5
Autor:
Deng, Tianchen, Shen, Guole, Qin, Tong, Wang, Jianyu, Zhao, Wentao, Wang, Jingchuan, Wang, Danwei, Chen, Weidong
Neural implicit scene representations have recently shown encouraging results in dense visual SLAM. However, existing methods produce low-quality scene reconstruction and low-accuracy localization performance when scaling up to large indoor scenes an
Externí odkaz:
http://arxiv.org/abs/2312.09866
The existing image steganography methods either sequentially conceal secret images or conceal a concatenation of multiple images. In such ways, the interference of information among multiple images will become increasingly severe when the number of s
Externí odkaz:
http://arxiv.org/abs/2309.08987
Autor:
Wu, Qitian, Zhao, Wentao, Yang, Chenxiao, Zhang, Hengrui, Nie, Fan, Jiang, Haitian, Bian, Yatao, Yan, Junchi
Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown promising
Externí odkaz:
http://arxiv.org/abs/2306.10759
Graph structure learning is a well-established problem that aims at optimizing graph structures adaptive to specific graph datasets to help message passing neural networks (i.e., GNNs) to yield effective and robust node embeddings. However, the commo
Externí odkaz:
http://arxiv.org/abs/2306.11264
Graph neural networks have been extensively studied for learning with inter-connected data. Despite this, recent evidence has revealed GNNs' deficiencies related to over-squashing, heterophily, handling long-range dependencies, edge incompleteness an
Externí odkaz:
http://arxiv.org/abs/2306.08385