A. Ben Hamza

A. Ben Hamza

Concordia University

H-index: 40

North America-Canada

Professor Information

University

Concordia University

Position

Professor Information Systems Engineering

Citations(all)

4603

Citations(since 2016)

1787

Cited By

3514

hIndex(all)

40

hIndex(since 2016)

24

i10Index(all)

93

i10Index(since 2016)

49

Email

University Profile Page

Concordia University

Research & Interests List

Computer vision

machine learning

federated learning

anomaly detection

human pose estimation

Co-Authors

H-index: 101
Alan S. Willsky

Alan S. Willsky

Massachusetts Institute of Technology

H-index: 40
Hamid Krim

Hamid Krim

North Carolina State University

H-index: 39
Jamal Bentahar

Jamal Bentahar

Concordia University

H-index: 38
Gozde Unal, PhD, Professor

Gozde Unal, PhD, Professor

Istanbul Teknik Üniversitesi

H-index: 32
Yong Zeng

Yong Zeng

Concordia University

H-index: 28
Nikos P. Pitsianis

Nikos P. Pitsianis

Aristotle University of Thessaloniki

H-index: 11
Hasib Zunair

Hasib Zunair

Concordia University

H-index: 5
Mahsa Rezaei

Mahsa Rezaei

Concordia University

H-index: 5
Hamed Ghodrati

Hamed Ghodrati

Concordia University

Professor FAQs

What is A. Ben Hamza's h-index at Concordia University?

The h-index of A. Ben Hamza has been 24 since 2016 and 40 in total.

What are A. Ben Hamza's research interests?

The research interests of A. Ben Hamza are: Computer vision, machine learning, federated learning, anomaly detection, human pose estimation

What is A. Ben Hamza's total number of citations?

A. Ben Hamza has 4,603 citations in total.

What are the co-authors of A. Ben Hamza?

The co-authors of A. Ben Hamza are Alan S. Willsky, Hamid Krim, Jamal Bentahar, Gozde Unal, PhD, Professor, Yong Zeng, Nikos P. Pitsianis, Hasib Zunair, Mahsa Rezaei, Hamed Ghodrati.

Top articles of A. Ben Hamza

Classification of developmental and brain disorders via graph convolutional aggregation

While graph convolution-based methods have become the de-facto standard for graph representation learning, their applications to disease prediction tasks remain quite limited, particularly in the classification of neurodevelopmental and neurodegenerative brain disorders. In this paper, we introduce an aggregator normalization graph convolutional network by leveraging aggregation in graph sampling, as well as skip connections and identity mapping. The proposed model learns discriminative graph node representations by incorporating both imaging and non-imaging features into the graph nodes and edges, respectively, with the aim of augmenting predictive capabilities and providing a holistic perspective on the underlying mechanisms of brain disorders. Skip connections enable the direct flow of information from the input features to later layers of the network, while identity mapping helps maintain the …

Authors

Ibrahim Salim,A Ben Hamza

Journal

Cognitive Computation

Publish By

Springer US

Publish Date

2024/3

RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving

Road scene understanding is crucial in autonomous driving, enabling machines to perceive the visual environment. However, recent object detectors tailored for learning on datasets collected from certain geographical locations struggle to generalize across different locations. In this paper, we present RSUD20K, a new dataset for road scene understanding, comprised of over 20K high-resolution images from the driving perspective on Bangladesh roads, and includes 130K bounding box annotations for 13 objects. This challenging dataset encompasses diverse road scenes, narrow streets and highways, featuring objects from different viewpoints and scenes from crowded environments with densely cluttered objects and various weather conditions. Our work significantly improves upon previous efforts, providing detailed annotations and increased object complexity. We thoroughly examine the dataset, benchmarking various state-of-the-art object detectors and exploring large vision models as image annotators.

Authors

Hasib Zunair,Shakib Khan,A Ben Hamza

Journal

arXiv preprint arXiv:2401.07322

Publish Date

2024/1/14

Learning to recognize occluded and small objects with partial inputs

Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based representations, and hence struggle to correctly recognize small and occluded objects. Intuitively, recognizing occluded objects requires knowledge of partial input, and hence context. Motivated by this intuition, we propose Masked Supervised Learning (MSL), a single-stage, model-agnostic learning paradigm for multi-label image recognition. The key idea is to learn context-based representations using a masked branch and to model label co-occurrence using label consistency. Experimental results demonstrate the simplicity, applicability and more importantly the competitive performance of MSL against previous state-of-the-art methods on standard multi-label image recognition benchmarks. In addition, we show that MSL is robust to random masking and demonstrate its effectiveness in recognizing non-masked objects. Code and pretrained models are available on GitHub.

Authors

Hasib Zunair,A Ben Hamza

Journal

Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Publish Date

2024

Adaptive spectral graph wavelets for collaborative filtering

Collaborative filtering is a popular approach in recommender systems, whose objective is to provide personalized item suggestions to potential users based on their purchase or browsing history. However, personalized recommendations require considerable amount of behavioral data on users, which is usually unavailable for new users, giving rise to the cold-start problem. To help alleviate this challenging problem, we introduce a spectral graph wavelet collaborative filtering framework for implicit feedback data, where users, items and their interactions are represented as a bipartite graph. Specifically, we first propose an adaptive transfer function by leveraging a power transform with the goal of stabilizing the variance of graph frequencies in the spectral domain. Then, we design a deep recommendation model for efficient learning of low-dimensional embeddings of users and items using spectral graph wavelets in an end-to-end fashion. In addition to capturing the graph's local and global structures, our approach yields localization of graph signals in both spatial and spectral domains, and hence not only learns discriminative representations of users and items, but also promotes the recommendation quality. The effectiveness of our proposed model is demonstrated through extensive experiments on real-world benchmark datasets, achieving better recommendation performance compared with strong baseline methods.

Authors

Osama Alshareet,A Ben Hamza

Journal

arXiv preprint arXiv:2312.03167

Publish Date

2023/12/5

Spatio-temporal MLP-graph network for 3D human pose estimation

Graph convolutional networks and their variants have shown significant promise in 3D human pose estimation. Despite their success, most of these methods only consider spatial correlations between body joints and do not take into account temporal correlations, thereby limiting their ability to capture relationships in the presence of occlusions and inherent ambiguity. To address this potential weakness, we propose a spatio-temporal network architecture composed of a joint-mixing multi-layer perceptron block that facilitates communication among different joints and a graph weighted Jacobi network block that enables communication among various feature channels. The major novelty of our approach lies in a new weighted Jacobi feature propagation rule obtained through graph filtering with implicit fairing. We leverage temporal information from the 2D pose sequences, and integrate weight modulation into the model to enable untangling of the feature transformations of distinct nodes. We also employ adjacency modulation with the aim of learning meaningful correlations beyond defined linkages between body joints by altering the graph topology through a learnable modulation matrix. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our model, outperforming recent state-of-the-art methods for 3D human pose estimation.

Authors

Tanvir Hassan,A Ben Hamza

Journal

Proc. British Machine Vision Conference (BMVC), 2023

Publish Date

2023/8/29

A graph encoder-decoder network for unsupervised anomaly detection

A key component of many graph neural networks (GNNs) is the pooling operation, which seeks to reduce the size of a graph while preserving important structural information. However, most existing graph pooling strategies rely on an assignment matrix obtained by employing a GNN layer, which is characterized by trainable parameters, often leading to significant computational complexity and a lack of interpretability in the pooling process. In this paper, we propose an unsupervised graph encoder–decoder model to detect abnormal nodes from graphs by learning an anomaly scoring function to rank nodes based on their degree of abnormality. In the encoding stage, we design a novel pooling mechanism, named LCPool, which leverages locality-constrained linear coding for feature encoding to find a cluster assignment matrix by solving a least-square optimization problem with a locality regularization term. By …

Authors

Mahsa Mesgaran,A Ben Hamza

Journal

Neural Computing and Applications

Publish Date

2023/8/15

Iterative graph filtering network for 3D human pose estimation

Graph convolutional networks (GCNs) have proven to be an effective approach for 3D human pose estimation. By naturally modeling the skeleton structure of the human body as a graph, GCNs are able to capture the spatial relationships between joints and learn an efficient representation of the underlying pose. However, most GCN-based methods use a shared weight matrix, making it challenging to accurately capture the different and complex relationships between joints. In this paper, we introduce an iterative graph filtering framework for 3D human pose estimation, which aims to predict the 3D joint positions given a set of 2D joint locations in images. Our approach builds upon the idea of iteratively solving graph filtering with Laplacian regularization via the Gauss–Seidel iterative method. Motivated by this iterative solution, we design a Gauss–Seidel network (GS-Net) architecture, which makes use of weight and …

Authors

Zaedul Islam,A Ben Hamza

Journal

Journal of Visual Communication and Image Representation

Publish Date

2023/7/31

Regular splitting graph network for 3D human pose estimation

In human pose estimation methods based on graph convolutional architectures, the human skeleton is usually modeled as an undirected graph whose nodes are body joints and edges are connections between neighboring joints. However, most of these methods tend to focus on learning relationships between body joints of the skeleton using first-order neighbors, ignoring higher-order neighbors and hence limiting their ability to exploit relationships between distant joints. In this paper, we introduce a higher-order regular splitting graph network (RS-Net) for 2D-to-3D human pose estimation using matrix splitting in conjunction with weight and adjacency modulation. The core idea is to capture long-range dependencies between body joints using multi-hop neighborhoods and also to learn different modulation vectors for different body joints as well as a modulation matrix added to the adjacency matrix associated to …

Authors

Tanvir Hassan,A Ben Hamza

Journal

IEEE Transactions on Image Processing

Publish Date

2023/5/9

academic-engine

Useful Links