Alessandro Gnutti

Bio: Alessandro Gnutti is an academic researcher from University of Brescia. The author has contributed to research in topics: Symmetry (geometry) & Computer science. The author has an hindex of 2, co-authored 14 publications receiving 34 citations.

Representation of signals by local symmetry decomposition

Abstract: In this paper we propose a segmentation of finite support sequences based on the even/odd decomposition of a signal. The objective is to ind a more compact representation of information. To this aim, the paper starts to generalize the even/odd decomposition by concentrating the energy on either the even or the odd part by optimally placing the centre of symmetry. Local symmetry intervals are thus located. The sequence segmentation is further processed by applying an iterative growth on the candidate segments to remove any overlapping portions. Experimental results show that the set of segments can be more eficiently compressed with respect to the DCT transformation of the entire sequence, which corresponds to the near optimal KLT transform of the data chosen for the experiment.

Automatic classification of mice vocalizations using Machine Learning techniques and Convolutional Neural Networks.

Abstract: Ultrasonic vocalizations (USVs) analysis is a well-recognized tool to investigate animal communication. It can be used for behavioral phenotyping of murine models of different disorders. The USVs are usually recorded with a microphone sensitive to ultrasound frequencies and they are analyzed by specific software. Different calls typologies exist, and each ultrasonic call can be manually classified, but the qualitative analysis is highly time-consuming. Considering this framework, in this work we proposed and evaluated a set of supervised learning methods for automatic USVs classification. This could represent a sustainable procedure to deeply analyze the ultrasonic communication, other than a standardized analysis. We used manually built datasets obtained by segmenting the USVs audio tracks analyzed with the Avisoft software, and then by labelling each of them into 10 representative classes. For the automatic classification task, we designed a Convolutional Neural Network that was trained receiving as input the spectrogram images associated to the segmented audio files. In addition, we also tested some other supervised learning algorithms, such as Support Vector Machine, Random Forest and Multilayer Perceptrons, exploiting informative numerical features extracted from the spectrograms. The performance showed how considering the whole time/frequency information of the spectrogram leads to significantly higher performance than considering a subset of numerical features. In the authors' opinion, the experimental results may represent a valuable benchmark for future work in this research field.

CANF-VC: Conditional Augmented Normalizing Flows for Video Compression

Abstract: This paper presents an end-to-end learning-based video compression system, termed CANF-VC, based on conditional augmented normalizing flows (CANF). Most learned video compression systems adopt the same hybrid-based coding architecture as the traditional codecs. Recent research on conditional coding has shown the sub-optimality of the hybrid-based coding and opens up opportunities for deep generative models to take a key role in creating new coding frameworks. CANF-VC represents a new attempt that leverages the conditional ANF to learn a video generative model for conditional inter-frame coding. We choose ANF because it is a special type of generative model, which includes variational autoencoder as a special case and is able to achieve better expressiveness. CANF-VC also extends the idea of conditional coding to motion coding, forming a purely conditional coding framework. Extensive experimental results on commonly used datasets confirm the superiority of CANF-VC to the state-of-the-art methods. The source code of CANF-VC is available at https://github.com/NYCU-MAPL/CANF-VC.

A wavelet filter comparison on multiple datasets for signal compression and denoising

Abstract: In this paper, we explicitly analyze the performance effects of several orthogonal and bi-orthogonal wavelet families. For each family, we explore the impact of the filter order (length) and the decomposition depth in the multiresolution representation. In particular, two contexts of use are examined: compression and denoising. In both cases, the experiments are carried out on a large dataset of different signal kinds, including various image sets and 1D signals (audio, electrocardiogram and seismic). Results for all the considered wavelets are shown on each dataset. Collectively, the study suggests that a meticulous choice of wavelet parameters significantly alters the performance of the above mentioned tasks. To the best of authors’ knowledge, this work represents the most complete analysis and comparison between wavelet filters. Therefore, it represents a valuable benchmark for future works.

Combining Appearance and Gradient Information for Image Symmetry Detection

Abstract: This work addresses the challenging problem of reflection symmetry detection in unconstrained environments. Starting from the understanding on how the visual cortex manages planar symmetry detection, it is proposed to treat the problem in two stages: i) the design of a stable metric that extracts subsets of consistently oriented candidate segments, whenever the underlying 2D signal appearance exhibits definite near symmetric correspondences; ii) the ranking of such segments on the basis of the surrounding gradient orientation specularity, in order to reflect real symmetric object boundaries. Since these operations are related to the way the human brain performs planar symmetry detection, a better correspondence can be established between the outcomes of the proposed algorithm and a human-constructed ground truth. When compared to the testing sets used in recent symmetry detection competitions, a remarkable performance gain can be observed. In additional, further validation has been achieved by conducting perceptual validation experiments with users on a newly built dataset.

Computational bioacoustics with deep learning: a review and roadmap

Abstract: Animal vocalisations and natural soundscapes are fascinating objects of study, and contain valuable evidence about animal behaviours, populations and ecosystems. They are studied in bioacoustics and ecoacoustics, with signal processing and analysis an important component. Computational bioacoustics has accelerated in recent decades due to the growth of affordable digital sound recording devices, and to huge progress in informatics such as big data, signal processing and machine learning. Methods are inherited from the wider field of deep learning, including speech and image processing. However, the tasks, demands and data characteristics are often different from those addressed in speech or music analysis. There remain unsolved problems, and tasks for which evidence is surely present in many acoustic signals, but not yet realised. In this paper I perform a review of the state of the art in deep learning for computational bioacoustics, aiming to clarify key concepts and identify and analyse knowledge gaps. Based on this, I offer a subjective but principled roadmap for computational bioacoustics with deep learning: topics that the community should aim to address, in order to make the most of future developments in AI and informatics, and to use audio data in answering zoological and ecological questions.

2017 ICCV Challenge: Detecting Symmetry in the Wild

Abstract: Motivated by various new applications of computational symmetry in computer vision and in an effort to advance machine perception of symmetry in the wild, we organize the third international symmetry detection challenge at ICCV 2017, after the CVPR 2011/2013 symmetry detection competitions. Our goal is to gauge the progress in computational symmetry with continuous benchmarking of both new algorithms and datasets, as well as more polished validation methodology. Different from previous years, this time we expand our training/testing data sets to include 3D data, and establish the most comprehensive and largest annotated datasets for symmetry detection to date; we also expand the types of symmetries to include densely-distributed and medial-axis-like symmetries; furthermore, we establish a challenge-and-paper dual track mechanism where both algorithms and articles on symmetry-related research are solicited. In this report, we provide a detailed summary of our evaluation methodology for each type of symmetry detection algorithm validated. We demonstrate and analyze quantified detection results in terms of precision-recall curves and F-measures for all algorithms evaluated. We also offer a short survey of the paper-track submissions accepted for our 2017 symmetry challenge.

Fast Graph Fourier Transforms Based on Graph Symmetry and Bipartition

Abstract: The graph Fourier transform (GFT) is an important tool for graph signal processing, with applications ranging from graph-based image processing to spectral clustering. However, unlike the discrete Fourier transform, the GFT typically does not have a fast algorithm. In this work, we develop new approaches to accelerate the GFT computation. In particular, we show that Haar units (Givens rotations with angle $\pi /4$ ) can be used to reduce GFT computation cost when the graph is bipartite or satisfies certain symmetry properties based on node pairing. We also propose a graph decomposition method based on graph topological symmetry, which allows us to identify and exploit butterfly structures in stages. This method is particularly useful for graphs that are nearly regular or have some specific structures, e.g., line graphs, cycle graphs, grid graphs, and human skeletal graphs. Though butterfly stages based on graph topological symmetry cannot be used for general graphs, they are useful in applications, including video compression and human action analysis, where symmetric graphs, such as symmetric line graphs and human skeletal graphs, are used. Our proposed fast GFT implementations are shown to reduce computation costs significantly, in terms of both number of operations and empirical runtimes.