Search Results for author: Nizar Bouguila

Found 13 papers, 8 papers with code

Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness

no code implementations7 Jun 2024 Zahra Golpayegani, Patrick St-Amant, Nizar Bouguila

By evaluating 39 types of data augmentations on a widely used OOD dataset, we demonstrate the impact of each data augmentation on the model's robustness to OOD data and further show that the mentioned hypothesis is not true; an increase in shape bias does not necessarily result in higher OOD robustness.

Data Augmentation

PatchSVD: A Non-uniform SVD-based Image Compression Algorithm

1 code implementation7 Jun 2024 Zahra Golpayegani, Nizar Bouguila

Storing data is particularly a challenge when dealing with image data which often involves large file sizes due to the high resolution and complexity of images.

Image Compression

Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition

2 code implementations1 Jun 2024 Alaa Nfissi, Wassim Bouachir, Nizar Bouguila, Brian Mishara

The proposed approach offers several advantages, including the identification and removal of irrelevant and redundant features, leading to a more effective model.

feature selection Speech Emotion Recognition

Unlocking the Emotional States of High-Risk Suicide Callers through Speech Analysis

1 code implementation IEEE 18th International Conference on Semantic Computing (ICSC) 2024 Alaa Nfissi, Wassim Bouachir, Nizar Bouguila, Brian Mishara

In light of these challenges, we present a novel end-to-end (E2E) method for speech emotion recognition (SER) as a mean of detecting changes in emotional state, that may indicate a high risk of suicide.

Speech Emotion Recognition

Semantic Segmentation Using Transfer Learning on Fisheye Images

no code implementations International Conference on Machine Learning and Applications (ICMLA) 2023 Sneha Paul, Zachary Patterson, Nizar Bouguila

This can be attributed to the fact that the models are not designed to handle fisheye images, and the available fisheye datasets are not sufficiently large to effectively train complex models.

Image Segmentation Segmentation +2

Automatic counting of planting microsites via local visual detection and global count estimation

no code implementations1 Nov 2023 Ahmed Zgaren, Wassim Bouachir, Nizar Bouguila

One of the main problems when planning planting operations is the difficulty in estimating the number of mounds present on a planting block, as their number may greatly vary depending on site characteristics.

DualMLP: a two-stream fusion model for 3D point cloud classification

1 code implementation The Visual Computer 2023 Sneha Paul, Zachary Patterson, Nizar Bouguila

The SparseNet, a relatively larger network, samples a small number of points from the complete point cloud, while the DenseNet, a lightweight network, takes in a larger number of points as input.

3D Point Cloud Classification Point Cloud Classification +1

CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud

1 code implementation 20th Conference on Robots and Vision (CRV) 2023 Sneha Paul, Zachary Patterson, Nizar Bouguila

In this study, we introduce a novel selfsupervised method called CrossMoCo, which learns the representations of unlabelled point cloud data in a multi-modal setup that also utilizes the 2D rendered images of the point clouds.

3D Object Classification 3D Point Cloud Linear Classification +4

CNN-n-GRU: end-to-end speech emotion recognition from raw waveform signal using CNNs and gated recurrent unit networks

no code implementations 21st IEEE International Conference on Machine Learning and Applications (ICMLA) 2023 Alaa Nfissi, Wassim Bouachir, Nizar Bouguila, Brian Mishara

Instead of using hand- crafted features or spectrograms, we train CNNs to recognise low-level speech representations from raw waveform, which allows the network to capture relevant narrow-band emotion characteristics.

Speech Emotion Recognition

Automatic counting of mounds on UAV images: combining instance segmentation and patch-level correction

no code implementations6 Sep 2022 Majid Nikougoftar Nategh, Ahmed Zgaren, Wassim Bouachir, Nizar Bouguila

Counting the number of mounds is generally conducted through manual field surveys by forestry workers, which is costly and prone to errors, especially for large areas.

Instance Segmentation object-detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.