Search Results for author:
Found 5 papers, 3 papers with code
Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks
However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards.
Text-independent writer identification using convolutional neural network
Randomly sampled tuples of images from the training set are used to train the CNN and aggregate the extracted local features of images from the tuples to form global features.
On modelling the emergence of logical thinking
In this paper, we argue than one of the most important aspects of the human mind is its capacity for logical thinking, which gives rise to many intellectual expressions that differentiate us from animal brains.
Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions
In this paper, we propose pattern generation strategies that generate shape and structural variations to improve the performance of recognition systems based on a small training set.
Learning Photography Aesthetics with Deep CNNs
To obtain both accuracy and human interpretation of the score, we advocate learning the aesthetic attributes along with the prediction of the overall score.
