Share This Author
LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
- Zejiang Shen, Ruochen Zhang, Melissa Dell, B. Lee, Jacob Carlson, Weining Li
- Computer ScienceICDAR
- 29 March 2021
The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout detection, character recognition, and many other document processing tasks and incorporates a community platform for sharing both pre-trained models and full document digitization pipelines.
A Novel Multi-Focus Images Fusion Method Based on Bidimensional Empirical Mode Decomposition
- Ying Chen, Yuanda Jiang, Chao Wang, Di Wang, Weining Li, G. Zhai
- Engineering2nd International Congress on Image and Signal…
- 30 October 2009
A novel images fusion method based on bidimensional empirical mode decomposition (BEMD) is proposed, aiming at solving the fusion problem of multi-focus images. BEMD is a new form of fully…
Vulnerability Detection for Source Code Using Contextual LSTM
- Aidong Xu, Tao Dai, Huajun Chen, Zhe Ming, Weining Li
- Computer Science5th International Conference on Systems and…
- 1 November 2018
This work proposed the vulnerability detection for source code using Contextual LSTM, which has the best performance for vulnerability detection, reaching the accuracy of 96.711% and the F1 score of 0.96984.
OLALA: Object-Level Active Learning for Efficient Document Layout Annotation
An Object-Level Active Learning framework for efficient document layout Annotation, OLALA, where only regions with the most ambiguous object predictions within an image are selected for annotators to label, optimizing the use of the annotation budget.
OLALA: Object-Level Active Learning Based Layout Annotation
This work introduces an Object-Level Active Learning based Layout Annotation framework, OLALA, which includes an object scoring method and a prediction correction algorithm that selects only the most ambiguous object prediction regions within an image for annotators to label, optimizing the use of the annotation budget.
Wildlife Action Recognition using Deep Learning
This work introduces an animal action dataset which can be used for generic animal action recognition and evaluates the proposed dataset on multiple approaches the I 3D model, a fusion network of I3D and VGG for scene semantic features, and a hierarchy of networks.