View-Invariant Analysis of Cyclic Motion

By S. M. Seitz, Charles R. Dyer. 1997

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

Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, background): “Since HOPC and STK-Distribution capture complimentary information, their combination significantly improves classification accuracy which is over 22% higher than the nearest competitor on both datasets.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, methodology): “In RGB videos, in order to recognize actions across viewpoint changes, mostly view independent representations are proposed such as view invariant spatio-temporal features [2,20,22,23,25,33].”
A survey of vision-based methods for action representation, segmentation and recognition (2011, background): “Similar, matrix factorization and rank constraints, as in structure from motion estimation [125], can be used to validate whether point correspondences in two images came from the same single rigid object [112,97].”
Recognizing action at a distance (2003, background): “Another class of methods analyze motion periodicity [10, 15, 5, 4].”
Actions as space-time shapes (2005, unknown): “Moreover, in cases of motion discontinuities, motion aliasing, and low-quality video, working with silhouettes may be advantageous over many existing methods ([3], [7], [10], [11], [15], [16], [17], [21], [20], [ 24 ], [25], [31], [33]) that compute optical flow, local space-time gradients, or other”
Actions as Space-Time Shapes (2007, unknown): “, [21], [24], [13]) and are thus limited to cyclic actions.”
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild (2020, methodology): “Periodicity has been used for various applications [9, 30, 32, 36] including temporal pattern classification [33].”
Machine Recognition of Human Activities: A Survey (2008, background): “Other related approaches for representa tion and recognition of quasi-cyclic actions have been proposed in [32], [33].”
View Invariance for Human Action Recognition (2005, background): “Seitz and Dyer (1997) have described an approach to detect cyclic motion that is affine invariant.”
Exploring the space of a human action (2005, methodology): “The first approach to use 3D constraints on 2D measurements was proposed by Seitz and Dyer in [14], where sufficient conditions for determining whether measurements were 2D affine projections of 3D cyclic motion were presented.”
View-Invariant Representation and Recognition of Actions (2002, methodology): “Following this observation, we restate the theorem given in Seitz and Dyer (1997) in the context of actions: Figure 17 .”