activity
20172022
most citedLearning sound representations using trainable COPE feature extractors

30 citations · 70 across the 8 of their papers we have counts for

collaborators

13 papers

cs.CL202230 cited

Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers

Stefan Haller, Adina Aldea, Christin Seifert +1

Automated short answer grading (ASAG) has gained attention in education as a means to scale educational tasks to the growing number of students. Recent progress in Natural Language…

cs.CV2021

Brain-inspired algorithms for processing of visual data

Nicola Strisciuglio

The study of the visual system of the brain has attracted the attention and interest of many neuro-scientists, that derived computational models of some types of neuron that compos…

cs.CV20202 cited

MTStereo 2.0: improved accuracy of stereo depth estimation withMax-trees

Rafael Brandt, Nicola Strisciuglio, Nicolai Petkov

Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo m…

cs.CV2019

Place recognition in gardens by learning visual representations: data set and benchmark analysis

Maria Leyva-Vallina, Nicola Strisciuglio, Nicolai Petkov

Visual place recognition is an important component of systems for camera localization and loop closure detection. It concerns the recognition of a previously visited place based on…

cs.CV20191 cited

A Push-Pull Layer Improves Robustness of Convolutional Neural Networks

Nicola Strisciuglio, Manuel Lopez-Antequera, Nicolai Petkov

We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images. We call this a push-pull la…

eess.AS201930 cited

Learning sound representations using trainable COPE feature extractors

Nicola Strisciuglio, Mario Vento, Nicolai Petkov

Sound analysis research has mainly been focused on speech and music processing. The deployed methodologies are not suitable for analysis of sounds with varying background noise, in…