Motion Segmentation in the Presence of Outlying, Incomplete, or Corrupted Trajectories

By Shankar R. Rao, Roberto Tron, René Vidal, Yi Ma. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

367 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e0bd3dd8d45d549728d0c9af9961f34c0f99ca0b

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit (2015, positive): “In many computer vision applications, such as motion segmentation [10, 35, 28], hand written digit clustering [41] and face clustering [4, 21], data from different classes can be well approximated by a union of low dimensional sub-spaces.”
Low rank subspace clustering (LRSC) (2014, methodology): “…statistical methods (Tipping and Bishop, 1999,Sugaya and Kanatani, 2004, Gruber and Weiss, 2004,Yang et al., 2006, Ma et al., 2007,Rao et al., 2008, Rao et al., 2010), and spectral clustering-based methods (Boult and Brown, 1991; Yan and Pollefeys, 2006; Zhang et al., 2010; Goh and Vidal, 2007;…”
Multi-Task Learning for Subspace Segmentation (2015, background): “…or subspace segmentation problem (these terms are used interchangeably) is relevant to numerous machine learning and computer vision applications, including image representation and compression (Hong et al., 2006), motion segmentation (Rao et al., 2010), and face clustering (Liu et al., 2013).”
Smooth Representation Clustering (2014, methodology): “Although there have been several new techniques developed to improve the criterion (e.g., agglomerative lossy compression (ALC) [ 22]), model selection (e.g., Branch and Bound (BB) [10]), the performance of these methods is limited by their dependency on estimating the exact subspace models.”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “An extension of SSC is developed by Rao et al. [128].”
Connections with Robust PCA and the Role of Emergent Sparsity in Variational Autoencoder Models (2018, background): “…of brevity here, with some mild additional conditions, Theorem 3 can naturally be extended to the case where the decoder mean function is generalized to subsume non-linear, union-of-subspace models as commonly assumed in subspace clustering problems (Elhamifar and Vidal, 2013; Rao et al., 2010).”
Latent Low-Rank Representation for subspace segmentation and feature extraction (2011, background): “In computer vision, subspace segmentation has been widely studied (e.g., [2, 3, 5, 7, 11, 17, 18, 19, 21, 22, 27]) owing to its numerous applications, such as motion segmentation [6, 21, 29], face recognition [26, 28] and image segmentation [15, 18].”
A closed form solution to robust subspace estimation and clustering (2011, methodology): “Table 2 compares our method against 1 -based ALC [15] and SSC [7].”
Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes (2014, methodology): “A wealth of motion segmentation algorithms for multi-rigid scenes have been proposed including algebraic frameworks such as GPCA [40] and methods that can deal with noise and outliers [29].”
Sparse Subspace Clustering: Algorithm, Theory, and Applications (2013, methodology): “Thus, by incorporating the corruption model of data into the sparse optimization program, we can deal with clustering of corrupted data as before, without explicitly running a separate algorithm to correct the errors in the data [21], [55].”
Consistent and Specific Multi-View Subspace Clustering (2018, background): “, representation learning (Liu and Yan 2011), motion segmentation (Rao et al. 2010) and image processing (Ma et al.”
Hidden Talents of the Variational Autoencoder. (2017, background): “Moreover, although we will defer to a formal treatment to future work for purposes of brevity here, with some mild additional conditions, Theorem 3 can naturally be extended to the case where the decoder mean function is generalized to subsume non-linear, union-of-subspace models as commonly assumed”
Sparse Subspace Clustering: Algorithm, Theory, and Applications (2012, methodology): “Therefore, there is a need for having clustering algorithms that take into account the multisubspace structure of the data.”
Robust Subspace Segmentation by Low-Rank Representation (2010, background): “Recently, the work of (Rao et al., 2009 ) to define the affinity matrix of an undirected graph.”