Zobrazeno 1 - 10
of 66 646
pro vyhledávání: '"Liu, li"'
Autor:
Chen, Xiaohui, Wang, Yinkai, He, Jiaxing, Du, Yuanqi, Hassoun, Soha, Xu, Xiaolin, Liu, Li-Ping
Graph generation is a critical task in numerous domains, including molecular design and social network analysis, due to its ability to model complex relationships and structured data. While most modern graph generative models utilize adjacency matrix
Externí odkaz:
http://arxiv.org/abs/2501.01073
Autor:
Chen, Hongyu, Wang, Zian, Qin, Peixin, Meng, Ziang, Zhou, Xiaorong, Wang, Xiaoning, Liu, Li, Zhao, Guojian, Duan, Zhiyuan, Zhang, Tianli, Liu, Jinghua, Shao, Dingfu, Liu, Zhiqi
The recently discovered altermagnets, featured by the exotic correlation of magnetic exchange interaction and alternating crystal environments, have offered exciting cutting-edge opportunities for spintronics. Here, we report the experimental observa
Externí odkaz:
http://arxiv.org/abs/2412.18220
Motivated by two news states $h_1(1911)$ and $h_1(2316)$ observed by BESIII, we have investigated the mass spectrum and the strong decay properties of the strangeonium mesons within the modified Godfrey-Isgur model by considering the screening effect
Externí odkaz:
http://arxiv.org/abs/2412.11498
Text-to-speech (TTS), also known as speech synthesis, is a prominent research area that aims to generate natural-sounding human speech from text. Recently, with the increasing industrial demand, TTS technologies have evolved beyond synthesizing human
Externí odkaz:
http://arxiv.org/abs/2412.06602
Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications. To this e
Externí odkaz:
http://arxiv.org/abs/2411.15761
Self-supervised learning has made substantial strides in image processing, while visual pre-training for autonomous driving is still in its infancy. Existing methods often focus on learning geometric scene information while neglecting texture or trea
Externí odkaz:
http://arxiv.org/abs/2411.12452
Autor:
Xu, Huali, Liu, Yongxiang, Liu, Li, Zhi, Shuaifeng, Sun, Shuzhou, Liu, Tianpeng, Cheng, MingMing
Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trained models (LMs) due to inaccessible source data and training strategi
Externí odkaz:
http://arxiv.org/abs/2411.10070
Predicting spatio-temporal traffic flow presents significant challenges due to complex interactions between spatial and temporal factors. Existing approaches often address these dimensions in isolation, neglecting their critical interdependencies. In
Externí odkaz:
http://arxiv.org/abs/2411.09251
The fundamental challenge in SAR target detection lies in developing discriminative, efficient, and robust representations of target characteristics within intricate non-cooperative environments. However, accurate target detection is impeded by facto
Externí odkaz:
http://arxiv.org/abs/2411.07500
Occlusion is a longstanding difficulty that challenges the UAV-based object detection. Many works address this problem by adapting the detection model. However, few of them exploit that the UAV could fundamentally improve detection performance by cha
Externí odkaz:
http://arxiv.org/abs/2411.04348