Zobrazeno 1 - 10
of 329
pro vyhledávání: '"Dufaux, P."'
Publikováno v:
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Nov 2024, Miami (FL), United States
Automatic metrics are used as proxies to evaluate abstractive summarization systems when human annotations are too expensive. To be useful, these metrics should be fine-grained, show a high correlation with human annotations, and ideally be independe
Externí odkaz:
http://arxiv.org/abs/2410.10867
Autor:
Wu, Ruituo, Chen, Yang, Xiao, Jian, Li, Bing, Fan, Jicong, Dufaux, Frédéric, Zhu, Ce, Liu, Yipeng
Cooperation between temporal convolutional networks (TCN) and graph convolutional networks (GCN) as a processing module has shown promising results in skeleton-based video anomaly detection (SVAD). However, to maintain a lightweight model with low co
Externí odkaz:
http://arxiv.org/abs/2406.02976
With the increased interest in immersive experiences, point cloud came to birth and was widely adopted as the first choice to represent 3D media. Besides several distortions that could affect the 3D content spanning from acquisition to rendering, eff
Externí odkaz:
http://arxiv.org/abs/2303.08634
Following the advent of immersive technologies and the increasing interest in representing interactive geometrical format, 3D Point Clouds (PC) have emerged as a promising solution and effective means to display 3D visual information. In addition to
Externí odkaz:
http://arxiv.org/abs/2211.02459
A Tone Mapping Operator (TMO) is required to render images with a High Dynamic Range (HDR) on media with limited dynamic capabilities. TMOs compress the dynamic range with the aim of preserving the visually perceptual cues of the scene. Previous lite
Externí odkaz:
http://arxiv.org/abs/2208.14113
Autor:
Abhishek Goswami, Erwan Bernard, Aru Ranjan Singh, Wolf Hauser, Frederic Dufaux, Rafal K. Mantiuk
Publikováno v:
IEEE Access, Vol 12, Pp 164210-164225 (2024)
A Tone Mapping Operator (TMO) is required to render images with a High Dynamic Range (HDR) on media with limited dynamic capabilities. TMOs compress the dynamic range with the aim of preserving the visually perceptual cues of the scene. Previous lite
Externí odkaz:
https://doaj.org/article/9960970fbda749b8b807ec0c0e6b162d
Autor:
C. Viatte, N. Guendouz, C. Dufaux, A. Hensen, D. Swart, M. Van Damme, L. Clarisse, P. Coheur, C. Clerbaux
Publikováno v:
Atmospheric Chemistry and Physics, Vol 23, Pp 15253-15267 (2023)
Ammonia (NH3) is an important air pollutant which, as a precursor of fine particulate matter, raises public health concerns. This study analyzes 2.5 years of NH3 observations derived from ground-based (miniDOAS; differential optical absorption spectr
Externí odkaz:
https://doaj.org/article/948a4b8d80c74892b99b80d678a9a7b2
In-loop filtering is used in video coding to process the reconstructed frame in order to remove blocking artifacts. With the development of convolutional neural networks (CNNs), CNNs have been explored for in-loop filtering considering it can be trea
Externí odkaz:
http://arxiv.org/abs/2106.12746
Point clouds are essential for storage and transmission of 3D content. As they can entail significant volumes of data, point cloud compression is crucial for practical usage. Recently, point cloud geometry compression approaches based on deep neural
Externí odkaz:
http://arxiv.org/abs/2102.12839
Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions
Externí odkaz:
http://arxiv.org/abs/2006.09043