Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Matching Shape Sequences in Video with Applications in Human Movement Analysis. Ieee Transactions on Pattern Analysis and Machine…

By Ashok Narayanan Veeraraghavan, Amit K. Roy-Chowdhury, Ramalingam Chellappa

How researchers see this paper

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

Citations in the corpus

Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, methodology): “Typical examples include shape silhouettes in the Kendall’s shape space [40, 3], linear dynamical systems on the Grassmann manifold [39], histograms of oriented optical flow on a hyper-sphere [11], and pairwise transformations of skeletal joints on a Lie group [41, 3, 42].”
A review of biometric technology along with trends and prospects (2014, unknown): “Table 1: Summary of hand region modalities: Modality Feature Set Recognition Techniques Datasets Fingerprint Ridge flow, ridge pattern, singular points, ridge skeleton, ridge flow, ridge ending, ridge contours, ridge kernel, orientation field, island, spur, crossover, learned feature, sweat pores, d”
A Review on Video-Based Human Activity Recognition (2013, methodology): “An exemplar-based sequential single-layered approach (as categorized in [95], where the approaches for human activity recognition are categorized into single-layered approaches and hierarchical approaches) for DTW is proposed in [16], and is used to attack speed variation.”
Moving vistas: Exploiting motion for describing scenes (2010, background): “As these examples illustrate, a scene may be composed of the same elements in similar relative spatial positions, but the manner in which they move in relation to each other can be exploited to obtain a better, fine-grained distinction in scene categories.”
Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold (2014, methodology): “In [28] human 71 silhouettes extracted from video images are used to represent the pose.”
Human gesture recognition on product manifolds (2012, methodology): “Particularly, we focus on the elements of tensor algebra, orthogonal groups, Stiefel manifolds, and Grassmann manifolds.”
Canonical Correlation Analysis of Video Volume Tensors for Action Categorization and Detection (2009, unknown): “Silhouette images have been used [2], [4].”
A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “Veeraraghavan et al. [93] proposed the DTW-based nonparametric models for the gait pattern problem.”
Elastic functional coding of human actions: From vector-fields to latent variables (2015, methodology): “Some of the popular non-Euclidean features used for activity analysis include shape silhouettes on the Kendall’s shape space [28], pairwise transformations of skeletal joints on SE(3)×SE(3) · · ·×SE(3) [29], linear dynamical system on the Grassmann manifold [25], and histogram of oriented optical fl”
Saliency Weighted Features for Person Re-identification (2014, unknown): “(ii) Features transformation based methods compute linear [15] and nonlinear [9,10,24,46] transformation functions that are used to project features between different camera-dependent spaces.”
Recurrent Attention Models for Depth-Based Person Identification (2016, background): “Originally proposed in [26], the gait energy image and ifigts variants [16, 6, 29, 66], embed temporal information onto a two-dimensional image by averaging the silhouette across all frames of a video.”