Sparse trace ratio LDA for supervised feature selection
Classification is a fundamental task in the field of data mining. Unfortunately, high-
dimensional data often degrade the performance of classification. To solve this problem …
dimensional data often degrade the performance of classification. To solve this problem …
Image-based freeform handwriting authentication with energy-oriented self-supervised learning
Freeform handwriting authentication verifies a person's identity from their writing style and
habits in messy handwriting data. This technique has gained widespread attention in recent …
habits in messy handwriting data. This technique has gained widespread attention in recent …
A general adaptive unsupervised feature selection with auto-weighting
Feature selection (FS) is essential in machine learning and data mining as it makes
handling high-dimensional data more efficient and reliable. More attention has been paid to …
handling high-dimensional data more efficient and reliable. More attention has been paid to …
A two-level rectification attention network for scene text recognition
Scene text recognition is a challenging task in the computer vision field due to the diversity
of text styles and the complexity of the image backgrounds. In recent decades, numerous …
of text styles and the complexity of the image backgrounds. In recent decades, numerous …
Demystifying Bitcoin address behavior via graph neural networks
Bitcoin is one of the decentralized cryptocurrencies powered by a peer-to-peer blockchain
network. Parties who trade in the bitcoin network are not required to disclose any personal …
network. Parties who trade in the bitcoin network are not required to disclose any personal …
Resparser: Fully convolutional multiple human parsing with representative sets
Y Dai, X Chen, X Wang, M Pang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Multiple human parsing (MHP) is typically treated as two sub-tasks, ie, instance separation
and body part segmentation. Existing methods usually tackle the sub-tasks by adopting a …
and body part segmentation. Existing methods usually tackle the sub-tasks by adopting a …
Graph neural networks in particle physics: Implementations, innovations, and challenges
S Thais, P Calafiura, G Chachamis, G DeZoort… - ar** strokes into
different semantic categories, has drawn considerable attention due to its wide applications …
different semantic categories, has drawn considerable attention due to its wide applications …