Recognizing action events from multiple viewpoints

By Tanveer Fathima Syeda-Mahmood, M. Alex O. Vasilescu, Saratendu Sethi. 2001

111 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

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

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): “ed and depth based methods. 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]. Some methods infer the 3D scene structure and use geometric transformations to a”
Recognizing human actions in videos acquired by uncalibrated moving cameras (2005, methodology): “To perform view invariant recognition of actions, all three approaches [1, 9, 10] use the epipolar geometry between the views of two stationary cameras.”
Non-intrusive human activity monitoring in a smart home environment (2013, background): “Many of these algorithms are based on analyzing human silhouettes , tr ating them as three-dimensional (3D) objects (space-time) and using 3D object recognition techniques to classify human actions [10], [11].”
A survey of vision-based methods for action representation, segmentation and recognition (2011, methodology): “Hence the resulting residual ∑ i |xiFxi| can be used as matching cost [123, 37, 114, 147, 148, 115].”
View-invariant human action recognition via robust locally adaptive multi-view learning (2015, methodology): “The first work that used the spatiotemporal volume was proposed by Syeda-Mahmood et al. (2001).”
Action Recognition from Arbitrary Views using 3 D Exemplars (2007, methodology): “Fundamental matrices can also be used to compare 2D action representations from different views, as joint trajectories in [16] [20] or silhouettes in [17].”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “Hybrid [25], [39], [40], [42], [47], [50], [54]–[56], [60], [67], [73], [88], [102], [107], [118], [135]”
Action Recognition from Arbitrary Views using 3D Exemplars (2007, methodology): “Fundamental matrices can also be used to compare 2D action representations from different views, as joint trajectories in [16, 20] or silhouettes in [17].”
Intelligent multi-camera video surveillance: A review (2013, background): “Many approaches (Rao et al., 2002; Junejo et al., 2008, 2011; Yilmaz and Shah, 2005; Syeda-Mahmood et al., 2001; Parameswaran and Chellappa, 2006; Shen and Foroosh, 2008; Ogale et al., 2006; Li et al., 2007; Weinland et al., 2007; Yan et al., 2008; Farhadi and Tabrizi, 2008; Liu et al., 2011) are…”
Cross-View Action Recognition from Temporal Self-similarities (2008, background): “Note also that this notion of self-similarity, unlike [5] or [3], does not require point correspondences or time-alignment between different actions to perform action recognition.”
View-Invariant Action Recognition from Point Triplets (2009, background): “An intriguing question that may arise is then the following: If this is true for any two scene planes, then why does the similarity measure based on the eigenvalue constraint proposed above work?”
Exploring the space of a human action (2005, methodology): “Syeda-Mahmood and Vasilescu proposed a view invariant method of concurrently estimating the fundamental matrix and recognizing actions in [15].”