Search Results for author: Djamila Aouada

Found 38 papers, 4 papers with code

CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention

no code implementations27 Feb 2024 Mohammad Sadil Khan, Elona Dupont, Sk Aziz Ali, Kseniya Cherenkova, Anis Kacem, Djamila Aouada

Thanks to its auto-regressive nature, CAD-SIGNet not only reconstructs a unique full design history of the corresponding CAD model given an input point cloud but also provides multiple plausible design choices.

3D Reconstruction CAD Reconstruction

LAA-Net: Localized Artifact Attention Network for High-Quality Deepfakes Detection

no code implementations24 Jan 2024 Dat Nguyen, Nesryne Mejri, Inder Pal Singh, Polina Kuleshova, Marcella Astrid, Anis Kacem, Enjie Ghorbel, Djamila Aouada

Second, an Enhanced Feature Pyramid Network (E-FPN) is proposed as a simple and effective mechanism for spreading discriminative low-level features into the final feature output, with the advantage of limiting redundancy.

DeepFake Detection Face Swapping +1

SPADES: A Realistic Spacecraft Pose Estimation Dataset using Event Sensing

no code implementations9 Nov 2023 Arunkumar Rathinam, Haytam Qadadri, Djamila Aouada

To facilitate further training and evaluation of DL-based models, we introduce a novel dataset, SPADES, comprising real event data acquired in a controlled laboratory environment and simulated event data using the same camera intrinsics.

Domain Adaptation Pose Estimation +1

Hardware Aware Evolutionary Neural Architecture Search using Representation Similarity Metric

no code implementations7 Nov 2023 Nilotpal Sinha, Abd El Rahman Shabayek, Anis Kacem, Peyman Rostami, Carl Shneider, Djamila Aouada

Our approach re-frames the neural architecture search problem as finding an architecture with performance similar to that of a reference model for a target hardware, while adhering to a cost constraint for that hardware.

Hardware Aware Neural Architecture Search Neural Architecture Search

SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines

1 code implementation30 Aug 2023 Dimitrios Mallis, Sk Aziz Ali, Elona Dupont, Kseniya Cherenkova, Ahmet Serdar Karadeniz, Mohammad Sadil Khan, Anis Kacem, Gleb Gusev, Djamila Aouada

In this paper, we define the proposed SHARP 2023 tracks, describe the provided datasets, and propose a set of baseline methods along with suitable evaluation metrics to assess the performance of the track solutions.

DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport

no code implementations14 Aug 2023 Sk Aziz Ali, Djamila Aouada, Gerd Reis, Didier Stricker

In this work, we propose (i) partial optimal transportation of LiDAR feature descriptor for robust LO estimation, (ii) joint learning of predictive uncertainty while learning odometry over driving sequences, and (iii) demonstrate how PU can serve as evidence for necessary pose-graph optimization when LO network is either under or over confident.

Motion Planning Robot Navigation

Space Debris: Are Deep Learning-based Image Enhancements part of the Solution?

no code implementations1 Aug 2023 Michele Jamrozik, Vincent Gaudillière, Mohamed Adel Musallam, Djamila Aouada

A visual comparison between the URes34P model developed in this work and the existing state of the art in deep learning image enhancement methods, relevant to images captured in space, is presented.

Image Enhancement

Impact of Disentanglement on Pruning Neural Networks

no code implementations19 Jul 2023 Carl Shneider, Peyman Rostami, Anis Kacem, Nilotpal Sinha, Abd El Rahman Shabayek, Djamila Aouada

Deploying deep learning neural networks on edge devices, to accomplish task specific objectives in the real-world, requires a reduction in their memory footprint, power consumption, and latency.

Disentanglement Model Compression

SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes

no code implementations13 Apr 2023 Kseniya Cherenkova, Elona Dupont, Anis Kacem, Ilya Arzhannikov, Gleb Gusev, Djamila Aouada

3D scanning as a technique to digitize objects in reality and create their 3D models, is used in many fields and areas.

3D-Aware Object Localization using Gaussian Implicit Occupancy Function

no code implementations3 Mar 2023 Vincent Gaudillière, Leo Pauly, Arunkumar Rathinam, Albert Garcia Sanchez, Mohamed Adel Musallam, Djamila Aouada

We then propose to have a new look at ellipse regression and replace the discontinuous geometric ellipse parameters with the parameters of an implicit Gaussian distribution encoding object occupancy in the image.

Object Object Localization +2

Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification

no code implementations25 Jan 2023 Indel Pal Singh, Enjie Ghorbel, Anis Kacem, Arunkumar Rathinam, Djamila Aouada

In this paper, a discriminator-free adversarial-based Unsupervised Domain Adaptation (UDA) for Multi-Label Image Classification (MLIC) referred to as DDA-MLIC is proposed.

Multi-Label Image Classification Unsupervised Domain Adaptation

Unsupervised Anomaly Detection in Time-series: An Extensive Evaluation and Analysis of State-of-the-art Methods

no code implementations6 Dec 2022 Nesryne Mejri, Laura Lopez-Fuentes, Kankana Roy, Pavel Chernakov, Enjie Ghorbel, Djamila Aouada

Notwithstanding the relevance of this topic in numerous application fields, a complete and extensive evaluation of recent state-of-the-art techniques is still missing.

Time Series Time Series Anomaly Detection +1

A New Perspective for Understanding Generalization Gap of Deep Neural Networks Trained with Large Batch Sizes

no code implementations21 Oct 2022 Oyebade K. Oyedotun, Konstantinos Papadopoulos, Djamila Aouada

As such, our main exposition in this paper is to investigate and provide new perspectives for the source of generalization loss for DNNs trained with a large batch size.

Model Optimization

Multi Label Image Classification using Adaptive Graph Convolutional Networks (ML-AGCN)

no code implementations ICIP 2022 Inder Pal Singh, Enjie Ghorbel, Oyebade Oyedotun, Djamila Aouada

In this paper, a novel graph-based approach for multi-label image classification called Multi-Label Adaptive Graph Convolutional Network (ML-AGCN) is introduced.

 Ranked #1 on Multi-Label Image Classification on MSCOCO (mean average precision metric)

Multi-Label Classification Multi-Label Image Classification

CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations

no code implementations22 Aug 2022 Elona Dupont, Kseniya Cherenkova, Anis Kacem, Sk Aziz Ali, Ilya Arzhannikov, Gleb Gusev, Djamila Aouada

3D reverse engineering is a long sought-after, yet not completely achieved goal in the Computer-Aided Design (CAD) industry.

TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network

1 code implementation18 Aug 2022 Ahmet Serdar Karadeniz, Sk Aziz Ali, Anis Kacem, Elona Dupont, Djamila Aouada

We propose a new neural network architecture for 3D body shape and high-resolution texture completion -- BCom-Net -- that can reconstruct the full geometry from mid-level to high-level partial input scans.

Leveraging Equivariant Features for Absolute Pose Regression

no code implementations CVPR 2022 Mohamed Adel Musallam, Vincent Gaudilliere, Miguel Ortiz del Castillo, Kassem Al Ismaeil, Djamila Aouada

While end-to-end approaches have achieved state-of-the-art performance in many perception tasks, they are not yet able to compete with 3D geometry-based methods in pose estimation.

Image Retrieval Pose Estimation +3

Disentangled Face Identity Representations for joint 3D Face Recognition and Expression Neutralisation

no code implementations20 Apr 2021 Anis Kacem, Kseniya Cherenkova, Djamila Aouada

The proposed network consists of three components; (1) a Graph Convolutional Autoencoder (GCA) to encode the 3D faces into latent representations, (2) a Generative Adversarial Network (GAN) that translates the latent representations of expressive faces into those of neutral faces, (3) and an identity recognition sub-network taking advantage of the neutralized latent representations for 3D face recognition.

Face Recognition Generative Adversarial Network

LSPnet: A 2D Localization-oriented Spacecraft Pose Estimation Neural Network

no code implementations19 Apr 2021 Albert Garcia, Mohamed Adel Musallam, Vincent Gaudilliere, Enjie Ghorbel, Kassem Al Ismaeil, Marcos Perez, Djamila Aouada

Being capable of estimating the pose of uncooperative objects in space has been proposed as a key asset for enabling safe close-proximity operations such as space rendezvous, in-orbit servicing and active debris removal.

Pose Estimation Spacecraft Pose Estimation

PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D

no code implementations12 Jan 2021 Kseniya Cherenkova, Djamila Aouada, Gleb Gusev

This dataset is used to learn a convolutional autoencoder for point clouds sampled from the pairs of 3D scans - CAD models.

3DBooSTeR: 3D Body Shape and Texture Recovery

no code implementations23 Oct 2020 Alexandre Saint, Anis Kacem, Kseniya Cherenkova, Djamila Aouada

The texture is subsequently obtained by projecting the partial texture onto the template mesh before inpainting the corresponding texture map with a novel approach.

Towards Generalization of 3D Human Pose Estimation In The Wild

no code implementations21 Apr 2020 Renato Baptista, Alexandre Saint, Kassem Al Ismaeil, Djamila Aouada

Retraining a state-of-the-art 3D pose estimation approach using data augmented with 3DBodyTex. Pose showed promising improvement in the overall performance, and a sensible decrease in the per joint position error when testing on challenging viewpoints.

3D Human Pose Estimation 3D Pose Estimation

Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition

no code implementations20 Dec 2019 Konstantinos Papadopoulos, Enjie Ghorbel, Djamila Aouada, Björn Ottersten

This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN).

Action Recognition Skeleton Based Action Recognition

Bi-objective Framework for Sensor Fusion in RGB-D Multi-View Systems: Applications in Calibration

no code implementations23 May 2019 Hassan Afzal, Djamila Aouada, Michel Antunes, David Fofi, Bruno Mirbach, Björn Ottersten

In this work, we propose a sensor fusion framework based on a weighted bi-objective optimization for refinement of extrinsic calibration tailored for RGB-D multi-view systems.

3D Reconstruction Sensor Fusion

Localized Trajectories for 2D and 3D Action Recognition

no code implementations10 Apr 2019 Konstantinos Papadopoulos, Girum Demisse, Enjie Ghorbel, Michel Antunes, Djamila Aouada, Björn Ottersten

The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion.

3D Action Recognition

A survey on Deep Learning Advances on Different 3D Data Representations

no code implementations4 Aug 2018 Eman Ahmed, Alexandre Saint, Abd El Rahman Shabayek, Kseniya Cherenkova, Rig Das, Gleb Gusev, Djamila Aouada, Bjorn Ottersten

3D data is a valuable asset the computer vision filed as it provides rich information about the full geometry of sensed objects and scenes.

Similarity Metric For Curved Shapes In Euclidean Space

no code implementations CVPR 2016 Girum G. Demisse, Djamila Aouada, Bjorn Ottersten

The use of direct product Lie groups to represent curved shapes led to an explicit formula for geodesic curves and the formulation of a similarity metric between shapes by the L2-norm on the Lie algebra.

Ensemble of Example-Dependent Cost-Sensitive Decision Trees

no code implementations18 May 2015 Alejandro Correa Bahnsen, Djamila Aouada, Bjorn Ottersten

Moreover, we propose two new cost-sensitive combination approaches; cost-sensitive weighted voting and cost-sensitive stacking, the latter being based on the cost-sensitive logistic regression method.

Fraud Detection General Classification +1

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