no code implementations • 17 Jan 2024 • David Picard
In this paper we propose a new non-linear classifier based on a combination of locally linear classifiers.
no code implementations • 17 Oct 2023 • Natacha Luka, Romain Negrel, David Picard
In recent research, Learned Image Compression has gained prominence for its capacity to outperform traditional handcrafted pipelines, especially at low bit-rates.
no code implementations • 22 Aug 2023 • Grégoire Petit, Michael Soumm, Eva Feillet, Adrian Popescu, Bertrand Delezoide, David Picard, Céline Hudelot
Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting.
1 code implementation • 5 Jun 2023 • Simon Lepage, Jérémie Mary, David Picard
This paper introduces a new challenge for image similarity search in the context of fashion, addressing the inherent ambiguity in this domain stemming from complex images.
no code implementations • 1 Feb 2023 • Marie-Morgane Paumard, Hedi Tabia, David Picard
Solving jigsaw puzzles requires to grasp the visual features of a sequence of patches and to explore efficiently a solution space that grows exponentially with the sequence length.
no code implementations • 20 Dec 2022 • Monika Wysoczańska, Tom Monnier, Tomasz Trzciński, David Picard
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks.
1 code implementation • ICCV 2023 • Yue Zhu, Nermin Samet, David Picard
We also propose three tasks: i) 3D whole-body pose lifting from 2D complete whole-body pose, ii) 3D whole-body pose lifting from 2D incomplete whole-body pose, and iii) 3D whole-body pose estimation from a single RGB image.
Ranked #2 on 3D Human Pose Estimation on H3WB
2 code implementations • 23 Nov 2022 • Grégoire Petit, Adrian Popescu, Hugo Schindler, David Picard, Bertrand Delezoide
Actual features of new classes and pseudo-features of past classes are fed into a linear classifier which is trained incrementally to discriminate between all classes.
1 code implementation • 10 Oct 2022 • Nicolas Dufour, David Picard, Vicky Kalogeiton
In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details.
Ranked #1 on Pose Transfer on CelebAMask-HQ
1 code implementation • 5 Oct 2022 • Yue Zhu, David Picard
3D human pose estimation is a challenging task because of the difficulty to acquire ground-truth data outside of controlled environments.
no code implementations • 14 Sep 2022 • Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard, Bertrand Delezoide
Mainstream methods need to store two deep models since they integrate new classes using fine-tuning with knowledge distillation from the previous incremental state.
no code implementations • 21 Jul 2022 • Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard
We investigate the relationship between the performance of these models and the geometry of their latent space.
no code implementations • 18 Jul 2022 • Victor Besnier, Andrei Bursuc, David Picard, Alexandre Briot
To address this issue, we build upon the recent ObsNet approach by providing object instance knowledge to the observer.
1 code implementation • 30 Nov 2021 • Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard
Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks.
no code implementations • 19 Nov 2021 • David Picard, Jérôme Fellus, Stéphane Garnier
This paper focuses on non-asymptotic diffusion time in asynchronous gossip protocols.
no code implementations • 19 Oct 2021 • Thibaut Issenhuth, Ugo Tanielian, David Picard, Jeremie Mary
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting different classes of images.
2 code implementations • 16 Sep 2021 • David Picard
In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision.
no code implementations • 18 Aug 2021 • Ryad Kaoua, Xi Shen, Alexandra Durr, Stavros Lazaris, David Picard, Mathieu Aubry
For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other.
1 code implementation • ICCV 2021 • Victor Besnier, Andrei Bursuc, David Picard, Alexandre Briot
In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic segmentation.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +2
no code implementations • 28 May 2021 • Victor Besnier, David Picard, Alexandre Briot
In this paper, we show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving, by triggering a fallback behavior if a target accuracy cannot be guaranteed.
no code implementations • 21 Mar 2021 • David Picard, Arsenia Chorti
In this study we present how to approach the problem of building efficient detectors for spectrally efficient frequency division multiplexing (SEFDM) systems.
no code implementations • 3 Mar 2021 • Arsenia Chorti, David Picard
In this work we compare the capacity and achievable rate of uncoded faster than Nyquist (FTN) signalling in the frequency domain, also referred to as spectrally efficient FDM (SEFDM).
no code implementations • 1 Jan 2021 • Thibaut Issenhuth, Ugo Tanielian, David Picard, Jeremie Mary
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting disconnected manifolds.
no code implementations • 4 Sep 2020 • Diogo Luvizon, Hedi Tabia, David Picard
In this paper we propose a highly scalable convolutional neural network, end-to-end trainable, for real-time 3D human pose regression from still RGB images.
Ranked #59 on 3D Human Pose Estimation on MPI-INF-3DHP
no code implementations • 11 Jun 2020 • Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein
In deep metric learning, the training procedure relies on sampling informative tuples.
no code implementations • 26 May 2020 • Marie-Morgane Paumard, David Picard, Hedi Tabia
We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions.
no code implementations • 30 Apr 2020 • Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein
Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks.
1 code implementation • 15 Dec 2019 • Diogo C. Luvizon, Hedi Tabia, David Picard
In this work, we propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences.
Ranked #141 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 21 Nov 2019 • Diogo C. Luvizon, Hedi Tabia, David Picard
3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint.
Ranked #68 on 3D Human Pose Estimation on Human3.6M
1 code implementation • ICCV 2019 • Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein
Although the metric learning part is well addressed, this metric is usually computed over the average of the extracted deep features.
Ranked #18 on Metric Learning on CUB-200-2011 (using extra training data)
no code implementations • ICLR 2019 • Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein
Learning rich and compact representations is an open topic in many fields such as object recognition or image retrieval.
no code implementations • ECCV 2018 • Marie-Morgane Paumard, David Picard, Hedi Tabia
This paper addresses the problem of reassembling images from disjointed fragments.
no code implementations • 5 Jul 2018 • Marie-Morgane Paumard, David Picard, Hedi Tabia
Archaeologists are in dire need of automated object reconstruction methods.
no code implementations • 23 Jun 2018 • Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein
Most image retrieval methods use global features that aggregate local distinctive patterns into a single representation.
1 code implementation • 2 May 2018 • Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Matthieu Cord
Recent advances in the machine learning community allowed different use cases to emerge, as its association to domains like cooking which created the computational cuisine.
1 code implementation • 30 Apr 2018 • Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Nicolas Thome, Matthieu Cord
Designing powerful tools that support cooking activities has rapidly gained popularity due to the massive amounts of available data, as well as recent advances in machine learning that are capable of analyzing them.
Ranked #9 on Cross-Modal Retrieval on Recipe1M
no code implementations • 4 Apr 2018 • Michael Blot, David Picard, Matthieu Cord
We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent.
2 code implementations • CVPR 2018 • Diogo C. Luvizon, David Picard, Hedi Tabia
Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature.
Ranked #1 on Action Recognition In Videos on NTU RGB+D
1 code implementation • 6 Oct 2017 • Diogo C. Luvizon, Hedi Tabia, David Picard
In this paper, we propose an end-to-end trainable regression approach for human pose estimation from still images.
Ranked #11 on Pose Estimation on Leeds Sports Poses
no code implementations • 31 Dec 2016 • David Picard
In this paper we propose a fast online Kernel SVM algorithm under tight budget constraints.
1 code implementation • 29 Nov 2016 • Michael Blot, David Picard, Matthieu Cord, Nicolas Thome
We address the issue of speeding up the training of convolutional networks.
no code implementations • CVPR 2014 • Hedi Tabia, Hamid Laga, David Picard, Philippe-Henri Gosselin
We evaluate the performance of the proposed Bag of Covariance Matrices framework on 3D shape matching and retrieval applications and demonstrate its superiority compared to descriptor-based techniques.