arXiv subjects

Vincent Leroy

Publications and source records attributed to Vincent Leroy.

23 records · Page 2Linked to original sources

arXiv2020

SMPLy Benchmarking 3D Human Pose Estimation in the Wild

Predicting 3D human pose from images has seen great recent improvements. Novel approaches that can even predict both pose and shape from a single input image have been introduced, often relying on a parametric model of the human body such as SMPL. While qualitative results for such methods are often shown for images captured in-the-wild, a proper benchmark in such conditions is still missing, as it is cumbersome to obtain ground-truth 3D poses elsewhere than in a motion capture room. This paper presents a pipeline to easily produce and validate such a dataset with accurate ground-truth, with which we benchmark recent 3D human pose estimation methods in-the-wild. We make use of the recently introduced Mannequin Challenge dataset which contains in-the-wild videos of people frozen in action like statues and leverage the fact that people are static and the camera moving to accurately fit the SMPL model on the sequences. A total of 24,428 frames with registered body models are then selected from 567 scenes at almost no cost, using only online RGB videos. We benchmark state-of-the-art SMPL-based human pose estimation methods on this dataset. Our results highlight that challenges remain, in particular for difficult poses or for scenes where the persons are partially truncated or occluded.

cs.CV↗

arXiv2020

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild

We introduce DOPE, the first method to detect and estimate whole-body 3D human poses, including bodies, hands and faces, in the wild. Achieving this level of details is key for a number of applications that require understanding the interactions of the people with each other or with the environment. The main challenge is the lack of in-the-wild data with labeled whole-body 3D poses. In previous work, training data has been annotated or generated for simpler tasks focusing on bodies, hands or faces separately. In this work, we propose to take advantage of these datasets to train independent experts for each part, namely a body, a hand and a face expert, and distill their knowledge into a single deep network designed for whole-body 2D-3D pose detection. In practice, given a training image with partial or no annotation, each part expert detects its subset of keypoints in 2D and 3D and the resulting estimations are combined to obtain whole-body pseudo ground-truth poses. A distillation loss encourages the whole-body predictions to mimic the experts' outputs. Our results show that this approach significantly outperforms the same whole-body model trained without distillation while staying close to the performance of the experts. Importantly, DOPE is computationally less demanding than the ensemble of experts and can achieve real-time performance. Test code and models are available at https://europe.naverlabs.com/research/computer-vision/dope.

cs.CV↗

arXiv2020

Mutation++: MUlticomponent Thermodynamic And Transport properties for IONized gases in C++

The Mutation++ library provides accurate and efficient computation of physicochemical properties associated with partially ionized gases in various degrees of thermal nonequilibrium. With v1.0.0, users can compute thermodynamic and transport properties, multiphase linearly-constrained equilibria, chemical production rates, energy transfer rates, and gas-surface interactions. The framework is based on an object-oriented design in C++, allowing users to plug-and-play various models, algorithms, and data as necessary. Mutation++ is available open-source under the GNU Lesser General Public License v3.0.

physics.comp-ph↗

arXiv2017

Ternary Neural Networks for Resource-Efficient AI Applications

The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we propose ternary neural networks (TNNs) in order to make deep learning more resource-efficient. We train these TNNs using a teacher-student approach based on a novel, layer-wise greedy methodology. Thanks to our two-stage training procedure, the teacher network is still able to use state-of-the-art methods such as dropout and batch normalization to increase accuracy and reduce training time. Using only ternary weights and activations, the student ternary network learns to mimic the behavior of its teacher network without using any multiplication. Unlike its -1,1 binary counterparts, a ternary neural network inherently prunes the smaller weights by setting them to zero during training. This makes them sparser and thus more energy-efficient. We design a purpose-built hardware architecture for TNNs and implement it on FPGA and ASIC. We evaluate TNNs on several benchmark datasets and demonstrate up to 3.1x better energy efficiency with respect to the state of the art while also improving accuracy.

cs.LG↗

arXiv2016

Testing Interestingness Measures in Practice: A Large-Scale Analysis of Buying Patterns

Understanding customer buying patterns is of great interest to the retail industry and has shown to benefit a wide variety of goals ranging from managing stocks to implementing loyalty programs. Association rule mining is a common technique for extracting correlations such as "people in the South of France buy rosé wine" or "customers who buy paté also buy salted butter and sour bread." Unfortunately, sifting through a high number of buying patterns is not useful in practice, because of the predominance of popular products in the top rules. As a result, a number of "interestingness" measures (over 30) have been proposed to rank rules. However, there is no agreement on which measures are more appropriate for retail data. Moreover, since pattern mining algorithms output thousands of association rules for each product, the ability for an analyst to rely on ranking measures to identify the most interesting ones is crucial. In this paper, we develop CAPA (Comparative Analysis of PAtterns), a framework that provides analysts with the ability to compare the outcome of interestingness measures applied to buying patterns in the retail industry. We report on how we used CAPA to compare 34 measures applied to over 1,800 stores of Intermarché, one of the largest food retailers in France.

cs.DB↗