Gait Recognition Using a View Transformation Model in the Frequency Domain

By Yasushi Makihara, R. Sagawa, Y. Mukaigawa, Tomio Echigo, Yasushi Yagi. European Conference on Computer Vision, 2006

488 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/a7f0f887ec8d089d579c04a4ca3a8fd3e48afb08

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, methodology): “The VTM method in [15] transforms a probe gait onto the virtue view that exists in the training database for multi-view gait recognition.”
Pattern Recognition (2018, unknown): “In [12,13] , cross-view projections were learned to transfer gait features from one view to another.”
A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs (2017, methodology): “Approaches to gait recognition in the recent literature can generally be grouped into two typical categories, i.e., model-based [7], [8], [30] and appearance-based [9], [10], [11], [12].”
The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition (2012, methodology): “In this paper, we deal with six such state-of-the-art gait features: GEI, Frequency-Domain Feature [4] (referred to as FDF in this paper), Gait Entropy Image (GEnI) [5], Masked GEI based on GEnI [7] (referred to as MGEI in this paper), Chrono-Gait Image (CGI) [6], and Gait Flow Image (GFI) [8].”
Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition (2018, methodology): “In a recognition phase, the VTM transforms gallery features into the same view angle as that of an input feature, and the features match under the same view.”
GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “In template matching approaches, View Transformation Model (VTM) learns a projection between different views (Makihara et al. 2006).”
Robust view transformation model for gait recognition (2011, methodology): “The difference is that Frequency-domain representation of Gait features (FG) are used rather than GEI in [6].”
GEINet: View-invariant gait recognition using a convolutional neural network (2016, methodology): “Additionally, it is noticeable that this accuracy improvement was not due to an input data type difference because even GEINet with FDF significantly outperformed the benchmarks, which had the same gait feature for the input data as the benchmarks.”
Gait recognition without subject cooperation (2010, background): “However, we note that a number existing approaches (Makihara et al., 2006; Kusakunniran et al., 2009) have been proposed recently to address the problem of view recognition and feature transformation across view.”
A model-based gait recognition method with body pose and human prior knowledge (2020, unknown): “Some cross-view gait recognition methods are FD-VTM [36] , RSVD-VTM [37] , RPCA-VTM [38] , R-VTM [39] , GP+CCA [40] and C3A [41] .”