N
Ning Lu
Publications - 9
Citations - 197
Ning Lu is an academic researcher. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 3, co-authored 3 publications receiving 67 citations.
Papers
More filters
Journal ArticleDOI
MASTER: Multi-aspect non-local network for scene text recognition
TL;DR: Wen et al. as discussed by the authors proposed MASTER, a self-attention based scene text recognizer that not only encodes the input-output attention but also learns selfattention which encodes feature-feature and target-target relationships inside the encoder and decoder and owns a great training efficiency because of high training parallelization and a high speed inference because of an efficient memory-cache mechanism.
Posted Content
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
TL;DR: PICK is introduced, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity.
Proceedings ArticleDOI
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
TL;DR: Wen et al. as discussed by the authors introduced Pick, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features.
Journal ArticleDOI
Large Language Models can be Guided to Evade AI-Generated Text Detection
TL;DR: The authors proposed Substitution-based In-Context example optimization method (SICO) to automatically generate such prompts, which enabled ChatGPT to evade six existing detectors, causing a significant 0.54 AUC drop on average.
Proceedings ArticleDOI
On Attacking Deep Image Quality Evaluator Via Spatial Transform
TL;DR: Luning et al. as discussed by the authors proposed an adversarial example generation method for attacking neural-based image quality assessment (IQA) by using image content deformation to avoid the loss of adversarial noise after compression.