Zobrazeno 1 - 10
of 414
pro vyhledávání: '"Brun, Luc"'
Recent studies introduced effective compression techniques for Large Language Models (LLMs) via post-training quantization or low-bit weight representation. Although quantized weights offer storage efficiency and allow for faster inference, existing
Externí odkaz:
http://arxiv.org/abs/2405.00632
In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries. In this paper, we p
Externí odkaz:
http://arxiv.org/abs/2309.07579
Publikováno v:
13th IAPR-TC15 International Workshop on Graph-Based Representations in Pattern Recognition (GbR 2023), Sep 2023, Vietri Sul Mare, Italy
Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allow
Externí odkaz:
http://arxiv.org/abs/2307.13011
Publikováno v:
Structural and Syntactic Pattern Recognition (SSPR), Aug 2022, Montr{\'e}al, Canada
Convolutional neural networks (CNN) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete grid into a reduced grid with the same connectivity and allows reduc
Externí odkaz:
http://arxiv.org/abs/2208.01648
This technical report is devoted to the continuous estimation of an epsilon-assignment. Roughly speaking, an epsilon assignment between two sets V1 and V2 may be understood as a bijective mapping between a sub part of V1 and a sub part of V2 . The re
Externí odkaz:
http://arxiv.org/abs/2111.14565
Publikováno v:
Pattern Recognition Letters 129, pages 19-25, 2020
The graph edit distance (GED) measures the dissimilarity between two graphs as the minimal cost of a sequence of elementary operations transforming one graph into another. This measure is fundamental in many areas such as structural pattern recogniti
Externí odkaz:
http://arxiv.org/abs/1907.02929
The graph edit distance (GED) is a flexible distance measure which is widely used for inexact graph matching. Since its exact computation is NP-hard, heuristics are used in practice. A popular approach is to obtain upper bounds for GED via transforma
Externí odkaz:
http://arxiv.org/abs/1907.00203
Publikováno v:
IAPR International workshop on Graph-Based Representation in Pattern Recognition, Donatello Conte, Jean-Yves Ramel, Jun 2019, Tours, France. pp.99-109
Computing a graph prototype may constitute a core element for clustering or classification tasks. However, its computation is an NP-Hard problem, even for simple classes of graphs. In this paper, we propose an efficient approach based on block coordi
Externí odkaz:
http://arxiv.org/abs/1906.11009
Publikováno v:
14th IEEE International Conference on Automatic Face and Gesture Recognition, May 2019, Lille, France
In this paper, we propose a new hand gesture recognition method based on skeletal data by learning SPD matrices with neural networks. We model the hand skeleton as a graph and introduce a neural network for SPD matrix learning, taking as input the 3D
Externí odkaz:
http://arxiv.org/abs/1905.07917
This paper proposes a new neural network based on SPD manifold learning for skeleton-based hand gesture recognition. Given the stream of hand's joint positions, our approach combines two aggregation processes on respectively spatial and temporal doma
Externí odkaz:
http://arxiv.org/abs/1904.12970