View-invariance in action recognition

By Cen Rao, Mubarak Shah. 2001

150 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

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].”
Behavior recognition via sparse spatio-temporal features (2005, background): “[24] use view invariant aspects of the trajectory of a tracked hand to differentiate between actions such as opening a cabinet or picking up an object.”
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots (2013, background): “While researchers have trained activity models from video data for many years, there is increasing interest in methods that can learn an action category from static image snapshots [17, 33, 34, 7, 36, 35].”
Learning a hierarchy of discriminative space-time neighborhood features for human action recognition (2010, background): “[27, 28, 24, 10, 29]), or alternatively, by forgoing direct body tracking and describing the overall appearance and motion patterns within a video clip (e.”
All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda (2021, background): “The captured body information is used to recognise the view-invariant action [407], [408].”
Exploring the space of a human action (2005, background): “Dynamic time warping has been a popular approach to account for highly non-linear transformations, [13].”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “Motion, frequency and others [15], [16], [23], [24], [26], [28], [29], [34], [35], [38], [79], [81], [82], [85], [87], [103], [106], [116], [117], [119], [122], [129]–[134]”
Capturing Global and Local Dynamics for Human Action Recognition (2014, background): “In single-layered approaches, sequence of images may be considered as 3D volume [16], trajectories [15], or spatiotemporal features.”
Accurate and real-time human action recognition based on 3D skeleton (2013, methodology): “[10] proposes a method to extract view-invariant features from body joints, while [11] uses a three-layer model to represent motion precisely.”
Recognizing action at a distance (2003, background): “Strategies such as [19, 12, 11] work best when we have data that support figures of this resolution.”
Understanding visuo‐motor primitives for motion synthesis and analysis (2006, background): “Mirror neurons would activate when a subject performs a specific action.”
EigenJoints-based action recognition using Naïve-Bayes-Nearest-Neighbor (2012, background): “Trajectory-based methods have also been widely explored for recognizing human activities [11] [14].”
A survey on activity recognition and behavior understanding in video surveillance (2013, unknown): “Rao [147]”
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].”
Recognising action as clouds of space-time interest points (2009, background): “Existing human action recognition methods can be broadly classified into four categories: flow based [4], spatio-temporal shape template based [7, 8, 21], interest points based [3, 18, 11, 17, 10, 6, 22], and tracking based [16, 1, 15, 19].”
Machine Recognition of Human Activities: A Survey (2008, background): “Cedras and Shah [3] present a survey on motion-based approaches to recognition as opposed to structure-based approaches .”
Gesture spotting with body-worn inertial sensors to detect user activities (2008, background): “…system for recognising classical ballet steps, Yamato et al. [10] worked on the recognition of different tennis strokes, Brand et al. [11] targeted T'ai Chi movements, Lee and Kim [12] dealt with typical gestures for interacting with a computer and Rao and Shah [13] aimed at manipulative gestures.”