Cross-View Action Recognition from Temporal Self-similarities

By Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patrick Pérez. 2008

263 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Cross-View Action Modeling, Learning, and Recognition (2014, background): “Self temporal similarity [7] characterizes actions with temporal selfsimilarities for cross-view action recognition.”
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, background): “Researchers have paid much attention to this issue and designed view-invariant approaches for action recognition from color videos [16, 30, 3, 32, 20, 7, 33, 41, 23, 15, 22, 43, 44, 25, 49, 29, 8].”
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, background): “Some attempts have been made in previous works to overcome the view variation problem for robust action recognition [3], [8], [9], [14], [15], [19], [24], [26], [31], [36], [37], [39], [40], [50], [52], [53], [60].”
The Action Similarity Labeling Challenge (2012, methodology): “Early sets, such as KTH [1] and Weizmann [2], have been extensively used to report action recognition performance (e.g., [18], [19], [20], [21], [22], [23], [24], to name a few).”
Making Action Recognition Robust to Occlusions and Viewpoint Changes (2010, background): “By contrast, in [10], actions are learned from arbitrary number of views by extracting view-invariant features based on frame-to-frame similarities within a sequence, which yields very stable features under difficult viewing conditions.”
Learning a Deep Model for Human Action Recognition from Novel Viewpoints (2016, methodology): “Other methods focus on view-invariant spatio-temporal features [33], [34], [35], [36], [37].”
Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling (2015, background): “Many efforts in this category focused on the design of good local volume detectors/descriptors [1], [9], [10], [11], [12], [13] or feature learning algorithms [14], [15], [16].”
Intelligent multi-camera video surveillance: A review (2013, methodology): “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…”
A survey of vision-based methods for action representation, segmentation and recognition (2011, background): “It is shown in [51] that such features remain surprisingly stable under changing viewing conditions.”
Cross-view activity recognition using Hankelets (2012, methodology): “Table 5 gives side by side the average accuracy using BoBHks with the accuracy of previous approaches [16, 7, 10, 6].”
Trajectory-Based Modeling of Human Actions with Motion Reference Points (2012, background): “The first category extracts/learns spatial-temporal local features where many efforts have been devoted to the design of good detectors/descriptors [1,7,8,9,10,11] or feature learning algorithms [12,13,14].”
View-invariant human action recognition via robust locally adaptive multi-view learning (2015, methodology): “Junejo et al. (2008) used the self-similarity of human motion trajectory and exploited the self-similarity matrix.”
Activity recognition using the velocity histories of tracked keypoints (2009, background): “’s temporal self-similarity features sacrifice all spatial information for extraordinary viewpoint invariance[10].”
Cross-View Action Recognition via Transferable Dictionary Learning (2016, background): “THE FOUR ACCURACY NUMBERS IN THE BRACKET ARE THE AVERAGE RECOGNITION ACCURACIES OF [16], [24], AND [29], THE PROPOSED UN-RSTDL AND UN-RLTDL RESPECTIVELY”
Cross-view action recognition via view knowledge transfer (2011, methodology): “We notice our performance is better than that of [2] and [16].”