Human activity analysis

By Jake K. Aggarwal, Michael S. Ryoo. 2011

1,339 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Computer Vision and Pattern Recognition

Citations in the corpus

A self-organizing neural network architecture for learning human-object interactions (2017, background): “The literature suggests a conceptual categorization of human activities into four diﬀerent levels depending on the complexity: gestures, actions, interactions, and group activities [24, 25, 26].”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, methodology): “[1] broadly classifies human activities into four categories: gestures, actions, interactions (with objects and others) and group activities.”
Learning Tags from Unsegmented Videos of Multiple Human Actions (2011, background): “There is now a fairly extensive literature [1] on video activity recognition and detection including approaches based on techniques such as dynamic Bayesian networks (DBNs) Figure 1.”
Exploring discriminative pose sub-patterns for effective action classification (2013, background): “Readers interested in more details can refer to some recent reviews [1, 24] on this topic.”
Video Action Detection with Relational Dynamic-Poselets (2014, background): “Action understanding in video [1] has attracted a great deal of attention in the computer vision community due to its wide applications in surveillance, human computer interaction, and content-based retrieval.”
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, background): “Recognizing and localizing human actions is an important and classic problem in computer vision [1, 7] with a wide range of applications including pervasive health-care, robotics, game control, etc.”
Skeleton-based action recognition via spatial and temporal transformer networks (2020, background): “Nevertheless, several aspects of skeleton-based action recognition still remain open (Zhang et al. (2019); Aggarwal and Ryoo (2011); Ren et al. (2020)).”
Sequential Max-Margin Event Detectors (2014, background): “Many problems in surveillance [14], activity analysis [1], clinical monitoring [20] and human computer interaction [12] can be posed as detecting events in time series.”
Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition (2020, background): “ecade, human action recognition becomes increasingly crucial and achieves promising progress in various applications, such as video surveillance, human-computer interaction, video retrieval and so on [1, 20, 29]. One essential problem in human action recognition is how to extract discriminative and ”
Clustered Spatio-temporal Manifolds for Online Action Recognition (2014, background): “1) is an action that comprises of the gestures "raising a hand" and "stretching an arm" [1].”
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization (2019, background): “Please refer to recent surveys [1, 3, 22, 19] for a detailed review.”
Pooled motion features for first-person videos (2014, background): “BoW and IFV are very commonly used feature representations in the activity recognition literature [1].”