Zobrazeno 1 - 10
of 6 399
pro vyhledávání: '"An, Yuanpeng"'
Autor:
Yang, Tsung-Han, Gao, Shang, Zhang, Yuanpeng, Olds, Daniel, Meier, William R., Stone, Matthew B., Sales, Brian C., Christianson, Andrew D., Zhang, Qiang
CoSn and FeSn, two kagome-lattice metals, have recently attracted significant attention as hosts of electronic flat bands and emergent physical properties. However, current understandings of their physical properties are limited to the knowledge of t
Externí odkaz:
http://arxiv.org/abs/2411.19464
Autor:
Huang, Bin, Wang, Siyu, Chen, Yuanpeng, Wu, Yidan, Song, Hui, Ding, Zifan, Leng, Jing, Liang, Chengpeng, Xue, Peng, Zhang, Junliang, Zhao, Tiankun
This technical report outlines the methodologies we applied for the PRCV Challenge, focusing on cognition and decision-making in driving scenarios. We employed InternVL-2.0, a pioneering open-source multi-modal model, and enhanced it by refining both
Externí odkaz:
http://arxiv.org/abs/2411.02999
Autor:
Wang, Ding, Wang, Ping, Mondal, Shubham, Hu, Mingtao, Wu, Yuanpeng, Wang, Danhao, Sun, Kai, Mi, Zetian
The pursuit of extreme device miniaturization and the exploration of novel physical phenomena have spurred significant interest in crystallographic phase control and ferroelectric switching in reduced dimensions. Recently, wurtzite ferroelectrics hav
Externí odkaz:
http://arxiv.org/abs/2408.02576
With the recent burst of 2D and 3D data, cross-modal retrieval has attracted increasing attention recently. However, manual labeling by non-experts will inevitably introduce corrupted annotations given ambiguous 2D/3D content. Though previous works h
Externí odkaz:
http://arxiv.org/abs/2407.17779
Autor:
He, Yuanpeng, Li, Lijian
Open-world long-tailed semi-supervised learning (OLSSL) has increasingly attracted attention. However, existing OLSSL algorithms generally assume that the distributions between known and novel categories are nearly identical. Against this backdrop, w
Externí odkaz:
http://arxiv.org/abs/2405.14516
In practical scenarios, time series forecasting necessitates not only accuracy but also efficiency. Consequently, the exploration of model architectures remains a perennially trending topic in research. To address these challenges, we propose a novel
Externí odkaz:
http://arxiv.org/abs/2405.06419
Autor:
He, Yuanpeng
Although current semi-supervised medical segmentation methods can achieve decent performance, they are still affected by the uncertainty in unlabeled data and model predictions, and there is currently a lack of effective strategies that can explore t
Externí odkaz:
http://arxiv.org/abs/2404.06181
Autor:
He, Yuanpeng, Li, Lijian
Although the existing uncertainty-based semi-supervised medical segmentation methods have achieved excellent performance, they usually only consider a single uncertainty evaluation, which often fails to solve the problem related to credibility comple
Externí odkaz:
http://arxiv.org/abs/2404.06177
Autor:
Dou, Shuguang, Jiang, Xiangyang, Tu, Yuanpeng, Gao, Junyao, Qu, Zefan, Zhao, Qingsong, Zhao, Cairong
The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or re
Externí odkaz:
http://arxiv.org/abs/2401.18032
Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples. Previous methods generally employ naive con
Externí odkaz:
http://arxiv.org/abs/2401.13325