Zobrazeno 1 - 10
of 615
pro vyhledávání: '"Huang, Yihua"'
The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar contents and
Externí odkaz:
http://arxiv.org/abs/2405.10029
Autor:
Yang, Ziyi, Gao, Xinyu, Sun, Yangtian, Huang, Yihua, Lyu, Xiaoyang, Zhou, Wen, Jiao, Shaohui, Qi, Xiaojuan, Jin, Xiaogang
The recent advancements in 3D Gaussian splatting (3D-GS) have not only facilitated real-time rendering through modern GPU rasterization pipelines but have also attained state-of-the-art rendering quality. Nevertheless, despite its exceptional renderi
Externí odkaz:
http://arxiv.org/abs/2402.15870
As the study of graph neural networks becomes more intensive and comprehensive, their robustness and security have received great research interest. The existing global attack methods treat all nodes in the graph as their attack targets. Although exi
Externí odkaz:
http://arxiv.org/abs/2308.07834
Heterogeneous graph neural networks (GNNs) have been successful in handling heterogeneous graphs. In existing heterogeneous GNNs, meta-path plays an essential role. However, recent work pointed out that simple homogeneous graph model without meta-pat
Externí odkaz:
http://arxiv.org/abs/2307.01636
Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural networks (GNNs) have received more and more attention. However, the existi
Externí odkaz:
http://arxiv.org/abs/2301.03049
Autor:
Xu, Zhuoer, Zhu, Guanghui, Meng, Changhua, Cui, Shiwen, Ying, Zhenzhe, Wang, Weiqiang, GU, Ming, Huang, Yihua
Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods have focused on different components of AT (e.g., designing loss func
Externí odkaz:
http://arxiv.org/abs/2210.03543
Autor:
Chen, Jingfan, Fan, Wenqi, Zhu, Guanghui, Zhao, Xiangyu, Yuan, Chunfeng, Li, Qing, Huang, Yihua
Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a ta
Externí odkaz:
http://arxiv.org/abs/2207.10307
Session-based recommendation is a challenging problem in the real-world scenes, e.g., ecommerce, short video platforms, and music platforms, which aims to predict the next click action based on the anonymous session. Recently, graph neural networks (
Externí odkaz:
http://arxiv.org/abs/2203.06407
Autor:
Mai, Chengcheng, Wang, Yuxiang, Gong, Ziyu, Wang, Hanxiang, Luo, Kaiwen, Yuan, Chunfeng, Huang, Yihua
Publikováno v:
In Expert Systems With Applications 15 November 2024 254
Autor:
Huang, Yingwei, Wang, Qiqi, Zhou, Weiwei, Jiang, Yawei, He, Kai, Huang, Wei, Feng, Yating, Wu, Hong, Liu, Lijuan, Pan, Yue, Huang, Yihua, Chen, Zirui, Li, Wei, Huang, Yaowei, Lin, Guanchuan, Zhang, Yulong, Ren, Yongyan, Xu, Kaibiao, Yu, Yanlin, Peng, Yuping, Pan, Xinghua, Pan, Suyue, Hu, Hailiang, Hu, Yafang
Publikováno v:
In Neoplasia November 2024 57