Outputs (8)

Reproducing "Show, attend and tell: Neural image caption generation with visual attention" (2023)
Presentation / Conference Contribution

This paper replicates the experiment presented in the work of Xu et al. [1], and
examines errors in the generated captions. The analysis of the identified errors aims to provide
deeper insight into the underlying causes. This study also encompass... Read More about Reproducing "Show, attend and tell: Neural image caption generation with visual attention".

Towards idea mining: Problem-solution phrase extraction from text (2022)
Presentation / Conference Contribution

This paper investigates the feasibility of problem-solution phrases extraction from scientific publications using neural network approaches. Bidirectional Long Short-Term Memory with Conditional Random Fields (Bi-LSTM-CRFs) and Bidirectional Encoder... Read More about Towards idea mining: Problem-solution phrase extraction from text.

Towards idea mining: Problem-solution phrases extraction from text (2022)
Presentation / Conference Contribution

This paper investigates the feasibility of problem-solution
phrases extraction from scientific publications using neural network approaches. Bidirectional Long Short-Term Memory with Conditional Random Fields (Bi-LSTM-CRFs) and Bidirectional Encoder... Read More about Towards idea mining: Problem-solution phrases extraction from text.

A generalised dropout mechanism for distributed systems (2022)
Journal Article

This letter uses a modified form of the NK model introduced to explore aspects of distributed control. In particular, a previous result suggesting the use of dynamically formed subgroups within the overall system can be more effective than global con... Read More about A generalised dropout mechanism for distributed systems.

Optimize transfer learning for lung diseases in bronchoscopy using a new concept: Sequential fine-tuning (2018)
Journal Article

Bronchoscopy inspection, as a follow-up procedure next to the radiological imaging, plays a key role in the diagnosis and treatment design for lung disease patients. When performing bronchoscopy, doctors have to make a decision immediately whether to... Read More about Optimize transfer learning for lung diseases in bronchoscopy using a new concept: Sequential fine-tuning.

Towards computation of novel ideas from corpora of scientific text (2015)
Presentation / Conference Contribution

© Springer International Publishing Switzerland 2015. In this work we present a method for the computation of novel ‘ideas’ from corpora of scientific text. The system functions by first detecting concept noun-phrases within the titles and abstracts... Read More about Towards computation of novel ideas from corpora of scientific text.

Incorporating texture features in a computer-aided breast lesion diagnosis system for automated three-dimensional breast ultrasound (2014)
Journal Article

We investigated the benefits of incorporating texture features into an existing computer-aided diagnosis (CAD) system for classifying benign and malignant lesions in automated three-dimensional breast ultrasound images. The existing system takes into... Read More about Incorporating texture features in a computer-aided breast lesion diagnosis system for automated three-dimensional breast ultrasound.

A method for finding implicating rules based on the genetic algorithm (2007)
Presentation / Conference Contribution

In information system, some rules have implicating relations (called implicating rules), but some rules have not. An approach of finding implicating rules based on the genetic algorithm is proposed. Some properties of independence and correlation of... Read More about A method for finding implicating rules based on the genetic algorithm.