no code implementations • 30 Jul 2024 • Raed Abdel-Sater, A. Ben Hamza
Long-term time series forecasting in centralized environments poses unique challenges regarding data privacy, communication overhead, and scalability.
1 code implementation • 26 Jul 2024 • Abu Taib Mohammed Shahjahan, A. Ben Hamza
Although graph convolutional networks exhibit promising performance in 3D human pose estimation, their reliance on one-hop neighbors limits their ability to capture high-order dependencies among body joints, crucial for mitigating uncertainty arising from occlusion or depth ambiguity.
1 code implementation • 24 Jul 2024 • Hasib Zunair, A. Ben Hamza
Localizing objects in an unsupervised manner poses significant challenges due to the absence of key visual information such as the appearance, type and number of objects, as well as the lack of labeled object classes typically available in supervised settings.
no code implementations • 5 May 2024 • Zaedul Islam, A. Ben Hamza
Accurate 3D human pose estimation is a challenging task due to occlusion and depth ambiguity.
1 code implementation • 14 Jan 2024 • Hasib Zunair, Shakib Khan, A. Ben Hamza
Road scene understanding is crucial in autonomous driving, enabling machines to perceive the visual environment.
no code implementations • 5 Dec 2023 • Osama Alshareet, A. Ben Hamza
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.
no code implementations • 13 Nov 2023 • Ibrahim Salim, A. Ben Hamza
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.
1 code implementation • 27 Oct 2023 • Hasib Zunair, A. Ben Hamza
Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small.
1 code implementation • 29 Aug 2023 • Tanvir Hassan, A. Ben Hamza
Graph convolutional networks and their variants have shown significant promise in 3D human pose estimation.
no code implementations • 15 Aug 2023 • Mahsa Mesgaran, A. Ben Hamza
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.
1 code implementation • 29 Jul 2023 • Zaedul Islam, A. Ben Hamza
Furthermore, we conduct ablation studies to analyze the contributions of different components of our model architecture and show that the skip connection and adjacency modulation help improve the model performance.
1 code implementation • 9 May 2023 • Tanvir Hassan, A. Ben Hamza
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.
Ranked #42 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
2 code implementations • 3 Oct 2022 • H. Zunair, Y. Gobeil, S. Mercier, A. Ben Hamza
Previous virtual try-on methods usually focus on aligning a clothing item with a person, limiting their ability to exploit the complex pose, shape and skin color of the person, as well as the overall structure of the clothing, which is vital to photo-realistic virtual try-on.
1 code implementation • 3 Oct 2022 • Hasib Zunair, A. Ben Hamza
Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance.
Ranked #105 on
Semantic Segmentation
on NYU Depth v2
no code implementations • 1 Nov 2021 • Jianning Quan, A. Ben Hamza
Estimating a 3D human pose has proven to be a challenging task, primarily because of the complexity of the human body joints, occlusions, and variability in lighting conditions.
Ranked #235 on
3D Human Pose Estimation
on Human3.6M
no code implementations • 18 Aug 2021 • Hasib Zunair, Yan Gobeil, Samuel Mercier, A. Ben Hamza
However, recent SSL methods rely on unlabeled image data at a scale of billions to work well.
1 code implementation • 26 Jul 2021 • Hasib Zunair, A. Ben Hamza
The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation.
1 code implementation • 17 Jun 2021 • Hasib Zunair, A. Ben Hamza
We introduce a new dataset called Synthetic COVID-19 Chest X-ray Dataset for training machine learning models.
no code implementations • 15 Apr 2021 • Ibrahim Salim, A. Ben Hamza
In this paper, we introduce a unified deep learning framework for bone age assessment using instance segmentation and ridge regression.
1 code implementation • 20 Oct 2020 • Hasib Zunair, A. Ben Hamza
Second, we show how our image synthesis method can serve as a data anonymization tool by achieving comparable detection performance when trained only on synthetic data.
1 code implementation • 20 Oct 2020 • Mahsa Mesgaran, A. Ben Hamza
The proposed layerwise propagation rule of our model is theoretically motivated by the concept of implicit fairing in geometry processing, and comprises a graph convolution module for aggregating information from immediate node neighbors and a skip connection module for combining layer-wise neighborhood representations.
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
no code implementations • 20 Oct 2020 • Mahsa Mesgaran, A. Ben Hamza
Graph convolutional networks learn effective node embeddings that have proven to be useful in achieving high-accuracy prediction results in semi-supervised learning tasks, such as node classification.
no code implementations • 20 Oct 2020 • Raed Abdel Sater, A. Ben Hamza
These devices sense the environment and generate multivariate temporal data of paramount importance for detecting anomalies and improving the prediction of energy usage in smart buildings.
1 code implementation • 14 Apr 2020 • Hasib Zunair, A. Ben Hamza
In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis by learning the inter-class mapping and synthesizing under-represented class samples from the over-represented ones using unpaired image-to-image translation.
no code implementations • 1 Mar 2020 • David Pickup, Xianfang Sun, Paul L. Rosin, Ralph R. Martin, Z Cheng, Zhouhui Lian, Masaki Aono, A. Ben Hamza, A Bronstein, M Bronstein, S Bu, Umberto Castellani, S Cheng, Valeria Garro, Andrea Giachetti, Afzal Godil, Luca Isaia, J. Han, Henry Johan, L Lai, Bo Li, C. Li, Haisheng Li, Roee Litman, X. Liu, Z Liu, Yijuan Lu, L. Sun, G Tam, Atsushi Tatsuma, J. Ye
In addition, further participants have also taken part, and we provide extra analysis of the retrieval results.
no code implementations • 8 Apr 2015 • Mohammed Khader, A. Ben Hamza
We propose a nonrigid registration approach for diffusion tensor images using a multicomponent information-theoretic measure.