2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019
DOI: 10.1109/cvpr.2019.00652
|View full text |Cite
|
Sign up to set email alerts
|

EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
66
0
2

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
4
1

Relationship

1
8

Authors

Journals

citations
Cited by 124 publications
(68 citation statements)
references
References 34 publications
0
66
0
2
Order By: Relevance
“…This approach involves five phases: visualization of the event stream, human figure detection, estimation of optical flow, human pose estimation, and gait recognition based on neural features. EV-Gait [ 19 ] collected several gait datasets using NVS and trains a convolutional neural network (CNN) to tackle the gait recognition problem. EV-Gait-GCN [ 20 ] applied a graph convolutional network (GCN) to identify human by the gait.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…This approach involves five phases: visualization of the event stream, human figure detection, estimation of optical flow, human pose estimation, and gait recognition based on neural features. EV-Gait [ 19 ] collected several gait datasets using NVS and trains a convolutional neural network (CNN) to tackle the gait recognition problem. EV-Gait-GCN [ 20 ] applied a graph convolutional network (GCN) to identify human by the gait.…”
Section: Related Workmentioning
confidence: 99%
“…Concretely, E2VID [ 12 ] is utilized to carry out the visualization attack, while EV-Gait (-IMG) [ 19 ] and EV-Gait-3DGraph [ 20 ] are used to perform the recognition attack. E2VID provides a well-trained end-to-end neural network to reconstruct images from a stream of events.…”
Section: Nvs and Privacy Challengesmentioning
confidence: 99%
“…In gait recognition, the system authenticates or classifies the target person by using her/his walking manner. The used gait data mainly include the following four modalities: camera image gait data [ 4 ], inertial acceleration sensor data [ 5 ], floor sensor data, and passive wireless signals [ 6 ] or wave radar data [ 7 ]. In addition, the recognition performance can be further improved by integrating the above four data modalities [ 8 ].…”
Section: Introductionmentioning
confidence: 99%
“…Castro et al [15] used a mixture of raw frames, optical, and depth information. Wang et al [16] used the information of dynamic vision sensors. Zhang et al [17] united GEIs, skeleton and RGB frame features to enhance robustness.…”
Section: Introductionmentioning
confidence: 99%