Filters








14 Hits in 8.2 sec

VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds [article]

Guanze Liu, Yu Rong, Lu Sheng
2021 arXiv   pre-print
By exploiting the rich complementary clues from the joint-level features and global features from the input point clouds, the proposed method encourages reliable and disentangled parameter predictions  ...  The proposed method achieves state-of-the-art performances on two large-scale datasets, namely SURREAL and DFAUST.  ...  In Computer Vision - ECCV 2016 Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016  ... 
arXiv:2110.08729v1 fatcat:3b25xw26qraalbtuuejmiqedwy

PAL DRs 6.4, 6.8, 6.12: Y4 Dissemination Report [article]

Michela Severgnini
2019 Zenodo  
It is the summary of three different WP6 Deliverables: Deliverable 6.4 "Website y4", Deliverable 6.8 "Publications and proceedings report y4" and Deliverable 6.12 "Dissemination events promoted y4"  ...  The present report describes the work carried out during the last project year regarding PAL's Dissemination and Communication activities.  ...  This paper was presented on The European Conference on Computer Vision (ECCV) Workshops, Munich, Germany, 8-14 September 2018. • How do children with diabetes evaluate the usability of a personal robot  ... 
doi:10.5281/zenodo.4632882 fatcat:rsjdrbpxvjdoffumtwf2o3pmaq

3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve [article]

Lei Wang, Jun Liu, Piotr Koniusz
2021 arXiv   pre-print
frames to achieve simultaneously the best alignment in the temporal and simulated camera viewpoint spaces for end-to-end learning under the limited few-shot training data.  ...  We demonstrate state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D Multiview Activity II.  ...  Skeleton-dml: Deep metric learning for - 14th European Conference, Amsterdam, The Netherlands, skeleton-based one-shot action recognition, 2021. 1, 3, 8, October 11-14, 2016, Proceedings  ... 
arXiv:2112.12668v1 fatcat:r3ivmqsdh5gnfglv5ox2jkm7gu

Robust and Efficient CPU-Based RGB-D Scene Reconstruction

Jianwei Li, Wei Gao, Heping Li, Fulin Tang, Yihong Wu
2018 Sensors  
3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along the camera trajectory, each view containing a small part of the scene.  ...  The key points in our approach include: (i) a robust and fast camera tracking method combining points and edges, which improves tracking stability in textureless scenes; (ii) an efficient data fusion strategy  ...  In Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 816 October 2016; pp. 500–516. 30.  ... 
doi:10.3390/s18113652 fatcat:6xzllz6v3rfrbpnb447f64cq5y

Human View Synthesis using a Single Sparse RGB-D Input [article]

Phong Nguyen, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkila, Tony Tung
2021 arXiv   pre-print
Novel view synthesis for humans in motion is a challenging computer vision problem that enables applications such as free-viewpoint video.  ...  Additionally, an enhancer network leverages the overall fidelity, even in occluded areas from the original view, producing crisp renders with fine details.  ...  Netherlands, October 11-14, 2016, Proceedings, Part II, vol- Graph., 32(3), July 2013. 3 ume 9906 of Lecture Notes in Computer Science, pages 311– [12] Qifeng  ... 
arXiv:2112.13889v2 fatcat:u6e2uuinxra2lnrknjmrcsd6yq

DRs 6.4, 6.8, 6.12: Y4 Dissemination Report

Michela Severgnini, Elettra Oleari
2019 Zenodo  
It is the summary of three different WP6 Deliverables: Deliverable 6.4 "Website y4", Deliverable 6.8 "Publications and proceedings report y4" and Deliverable 6.12 "Dissemination events promoted y4"  ...  The present report describes the work carried out during the last project year regarding PAL's Dissemination and Communication activities.  ...  The paper has been presented during the Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS) 2019 in Siracusa, Italy, on the 24-26 April 2019.  ... 
doi:10.5281/zenodo.3443714 fatcat:477acn7fpzem7fue453gl35t7a

Representations and Benchmarking of Modern Visual SLAM Systems

Yuchen Cao, Lan Hu, Laurent Kneip
2020 Sensors  
and semantic annotations of the recovered 3D model.  ...  We discuss the structure of the representations and optimisation problems involved in Spatial AI, and propose new synthetic datasets that, for the first time, include accurate ground truth information  ...  In Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 11–14 October 2016. 11. Qin, T.; Li, P.; Shen, S.  ... 
doi:10.3390/s20092572 pmid:32366018 pmcid:PMC7248763 fatcat:myrm7wcqtfghxgptlnbphhk3p4

A Survey of Deep Active Learning [article]

Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
2021 arXiv   pre-print
Finally, we discussed the confusion and problems in DAL, and gave some possible development directions for DAL.  ...  In addition, we also analyzed and summarized the development of DAL from the perspective of application.  ...  In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI (Lecture Notes in Computer Science, Vol. 9910).  ... 
arXiv:2009.00236v2 fatcat:zuk2doushzhlfaufcyhoktxj7e

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios [article]

Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow
2021 arXiv   pre-print
Motivated by the recent fundamental changes towards neural models and the popular pre-train and fine-tune paradigm, we survey promising approaches for low-resource natural language processing.  ...  This includes mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision.  ...  Distant super- the 18th BioNLP Workshop and Shared Task, pages vision from disparate sources for low-resource part- 105–114, Florence, Italy.  ... 
arXiv:2010.12309v3 fatcat:26dwmlkmn5auha2ob2qdlrvla4

FCAU-Net for the Semantic Segmentation of Fine-Resolution Remotely Sensed Images

Xuerui Niu, Qiaolin Zeng, Xiaobo Luo, Liangfu Chen
2022 Remote Sensing  
capturing position information and channel relationships; (2) the ACB enhances the feature representation ability of the standard convolution layer and captures and refines the feature information in  ...  the fitting residuals of the fused features, and improves the ability of the network to capture information flows.  ...  In Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 816 October 2018; pp. 3–19. 47. Hou, Q.B.; Zhou, D.Q.; Feng, J.S.  ... 
doi:10.3390/rs14010215 fatcat:gfnv5kbdk5a4tepwcwd7tmiihe

Quasi-hyperbolic momentum and Adam for deep learning [article]

Jerry Ma, Denis Yarats
2019 arXiv   pre-print
We hope that these empirical results, combined with the conceptual and practical simplicity of QHM and QHAdam, will spur interest from both practitioners and researchers.  ...  We describe numerous connections to and identities with other algorithms, and we characterize the set of two-state optimization algorithms that QHM can recover.  ...  ACKNOWLEDGMENTS We thank Aaron Defazio, Nicolas Loizou, Yann Olivier, Mark Tygert, and anonymous reviewers and commenters for insightful discussions and valuable suggestions.  ... 
arXiv:1810.06801v4 fatcat:tq3iul7mdnhjhjjtq5d7edjacm

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022
As a result, a growing community of algorithmic fairness researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of the risks and opportunities  ...  the three most popular fairness datasets, namely Adult, COMPAS and German Credit.  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc  ... 
doi:10.48550/arxiv.2202.01711 fatcat:mav36x3w5namjhurzpevtsmsju

Machine learning for human performance capture from multi-viewpoint video

Matthew Trumble
2019
The need to call the actor for a second day of shooting in a specialised motion capture (mo-cap) facility is avoided, saving time and money, since performance capture was possible without corrupting the  ...  Furthermore, if such performance capture data is available in real-time, the director may immediately pre-visualize the look and feel of the final character animation enabling tighter capture iteration  ...  In Hua, G. and Jégou, H., editors, Computer Vision -ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III, pages 871-878.  ... 
doi:10.15126/thesis.00850064 fatcat:octvu4ecczagdog3w6kc4k6gna

Study of the effect made by interval hypoxic training on cardiac metabolism and hemodynamics

T. Voronina, E.Y. Bersenev, G.P. Stepanova, V.V. Pyatenko, I.А. Berseneva, N.N. Chernov, L.V. Smekalkina, B.А. Yuldashev, M.D. Murodova
2021
oxygen and 79.1% nitrogen) during the 45-minute session.  ...  Figure 1 given herein shows the ECG and rheogram curves recorded before and after exposure to interval hypoxic training (IHT).  ...  In Proceedings of the 4th Workshop Informatics. 2019. ArXiv, abs/1911.06270. on Middleware for Edge Clouds & Cloudlets (pp. 1-6). 20. Xue C, et al. Transferable AutoML by Model Shar- 10.  ... 
doi:10.18137/cardiometry.2021.20.89 fatcat:ostds5luj5dljgssbxbnkp3ypq