Zobrazeno 1 - 10
of 2 749
pro vyhledávání: '"YANG, LAURENCE T."'
Autor:
Li, Zhe, Yuan, Weihao, He, Yisheng, Qiu, Lingteng, Zhu, Shenhao, Gu, Xiaodong, Shen, Weichao, Dong, Yuan, Dong, Zilong, Yang, Laurence T.
Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP's pretraining on static image-
Externí odkaz:
http://arxiv.org/abs/2410.07093
Dynamic Searchable Encryption (DSE) has emerged as a solution to efficiently handle and protect large-scale data storage in encrypted databases (EDBs). Volume leakage poses a significant threat, as it enables adversaries to reconstruct search queries
Externí odkaz:
http://arxiv.org/abs/2403.01182
Searchable symmetric encryption schemes often unintentionally disclose certain sensitive information, such as access, volume, and search patterns. Attackers can exploit such leakages and other available knowledge related to the user's database to rec
Externí odkaz:
http://arxiv.org/abs/2403.01155
Autor:
Li, Zhe, Zhang, Ziyang, Zhao, Jinglin, Wang, Zheng, Ren, Bocheng, Liu, Debin, Yang, Laurence T.
Masked autoencoding and generative pretraining have achieved remarkable success in computer vision and natural language processing, and more recently, they have been extended to the point cloud domain. Nevertheless, existing point cloud models suffer
Externí odkaz:
http://arxiv.org/abs/2402.02088
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the multi-granula
Externí odkaz:
http://arxiv.org/abs/2402.02045
The pre-training architectures of large language models encompass various types, including autoencoding models, autoregressive models, and encoder-decoder models. We posit that any modality can potentially benefit from a large language model, as long
Externí odkaz:
http://arxiv.org/abs/2310.16861
Graph neural networks (GNNs) have shown great ability in modeling graphs, however, their performance would significantly degrade when there are noisy edges connecting nodes from different classes. To alleviate negative effect of noisy edges on neighb
Externí odkaz:
http://arxiv.org/abs/2309.07380
Searchable symmetric encryption enables private queries over an encrypted database, but it also yields information leakages. Adversaries can exploit these leakages to launch injection attacks (Zhang et al., USENIX'16) to recover the underlying keywor
Externí odkaz:
http://arxiv.org/abs/2302.05628
Publikováno v:
Proceedings of AAAI Conference on Artificial Intelligence (AAAI), pp. 9782-9791, 2023
Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to various grap
Externí odkaz:
http://arxiv.org/abs/2301.01404
Recent research about camouflaged object detection (COD) aims to segment highly concealed objects hidden in complex surroundings. The tiny, fuzzy camouflaged objects result in visually indistinguishable properties. However, current single-view COD de
Externí odkaz:
http://arxiv.org/abs/2210.06361