no code implementations • 27 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.
no code implementations • 24 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.
no code implementations • 9 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.
no code implementations • 7 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
1 code implementation • 30 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.
no code implementations • 14 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.
no code implementations • 1 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.
no code implementations • 19 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.
1 code implementation • ICASSP 2023 • Nesryne Mejri, Enjie Ghorbel, Djamila Aouada
This paper introduces a novel framework for unsupervised type-agnostic deepfake detection called UNTAG.
1 code implementation • 22 May 2023 • Ashish Sinha, Jeremy Kawahara, Arezou Pakzad, Kumar Abhishek, Matthieu Ruthven, Enjie Ghorbel, Anis Kacem, Djamila Aouada, Ghassan Hamarneh
In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis.
no code implementations • 12 May 2023 • Leo Pauly, Wassim Rharbaoui, Carl Shneider, Arunkumar Rathinam, Vincent Gaudilliere, Djamila Aouada
The primary goal of this survey is to describe the current DL-based methods for spacecraft pose estimation in a comprehensive manner.
no code implementations • 13 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.
no code implementations • 4 Mar 2023 • Mohamed Adel Musallam, Vincent Gaudillière, Djamila Aouada
Visual place recognition is a key to unlocking spatial navigation for animals, humans and robots.
no code implementations • 3 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.
no code implementations • 25 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
no code implementations • 11 Jan 2023 • Indel Pal Singh, Enjie Ghorbel, Oyebade Oyedotun, Djamila Aouada
This paper proposes an adaptive graph-based approach for multi-label image classification.
no code implementations • 6 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.
no code implementations • 21 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.
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)
no code implementations • 22 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.
1 code implementation • 18 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.
no code implementations • 18 Aug 2022 • Leo Pauly, Michele Lynn Jamrozik, Miguel Ortiz del Castillo, Olivia Borgue, Inder Pal Singh, Mohatashem Reyaz Makhdoomi, Olga-Orsalia Christidi-Loumpasefski, Vincent Gaudilliere, Carol Martinez, Arunkumar Rathinam, Andreas Hein, Miguel Olivares-Mendez, Djamila Aouada
From the lessons learned during the lab development, this article presents a systematic approach combining market survey and experimental analyses for equipment selection.
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.
no code implementations • 20 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.
no code implementations • 19 Apr 2021 • Konstantinos Papadopoulos, Anis Kacem, Abdelrahman Shabayek, Djamila Aouada
This has two disadvantages.
no code implementations • 19 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.
no code implementations • 13 Apr 2021 • Mohamed Adel Musallam, Kassem Al Ismaeil, Oyebade Oyedotun, Marcos Damian Perez, Michel Poucet, Djamila Aouada
This paper proposes the SPARK dataset as a new unique space object multi-modal image dataset.
no code implementations • 12 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.
no code implementations • 26 Oct 2020 • Alexandre Saint, Anis Kacem, Kseniya Cherenkova, Konstantinos Papadopoulos, Julian Chibane, Gerard Pons-Moll, Gleb Gusev, David Fofi, Djamila Aouada, Bjorn Ottersten
Additionally, two unique datasets of 3D scans are proposed, to provide raw ground-truth data for the benchmarks.
no code implementations • 23 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.
no code implementations • 21 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.
Ranked #251 on 3D Human Pose Estimation on Human3.6M
no code implementations • 20 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).
Ranked #11 on Action Recognition on NTU RGB+D 120
no code implementations • 23 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.
no code implementations • 10 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.
no code implementations • 4 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.
no code implementations • CVPR 2017 • Michel Antunes, Joao P. Barreto, Djamila Aouada, Bjorn Ottersten
The article concerns the automatic calibration of a camera with radial distortion from a single image.
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.
no code implementations • 18 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.