Zobrazeno 1 - 10
of 301
pro vyhledávání: '"Pu Shiliang"'
Previous face forgery detection methods mainly focus on appearance features, which may be easily attacked by sophisticated manipulation. Considering the majority of current face manipulation methods generate fake faces based on a single frame, which
Externí odkaz:
http://arxiv.org/abs/2403.05172
Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface approximation and
Externí odkaz:
http://arxiv.org/abs/2403.05117
Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to address this k
Externí odkaz:
http://arxiv.org/abs/2403.00258
Autor:
Dou, Shihan, Zhou, Enyu, Liu, Yan, Gao, Songyang, Zhao, Jun, Shen, Wei, Zhou, Yuhao, Xi, Zhiheng, Wang, Xiao, Fan, Xiaoran, Pu, Shiliang, Zhu, Jiang, Zheng, Rui, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks. Increasing instruction data substantially is a direct solution to alig
Externí odkaz:
http://arxiv.org/abs/2312.09979
Distantly supervised named entity recognition (DS-NER) aims to locate entity mentions and classify their types with only knowledge bases or gazetteers and unlabeled corpus. However, distant annotations are noisy and degrade the performance of NER mod
Externí odkaz:
http://arxiv.org/abs/2310.08298
Network embedding, a graph representation learning method illustrating network topology by mapping nodes into lower-dimension vectors, is challenging to accommodate the ever-changing dynamic graphs in practice. Existing research is mainly based on no
Externí odkaz:
http://arxiv.org/abs/2306.08967
Iris presentation attack detection (PAD) has achieved great success under intra-domain settings but easily degrades on unseen domains. Conventional domain generalization methods mitigate the gap by learning domain-invariant features. However, they ig
Externí odkaz:
http://arxiv.org/abs/2305.12800
Taxonomy completion, enriching existing taxonomies by inserting new concepts as parents or attaching them as children, has gained significant interest. Previous approaches embed concepts as vectors in Euclidean space, which makes it difficult to mode
Externí odkaz:
http://arxiv.org/abs/2305.11004
Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source domains via d
Externí odkaz:
http://arxiv.org/abs/2304.02950
Most existing approaches for point cloud normal estimation aim to locally fit a geometric surface and calculate the normal from the fitted surface. Recently, learning-based methods have adopted a routine of predicting point-wise weights to solve the
Externí odkaz:
http://arxiv.org/abs/2303.17167