Machine Recognition of Human Activities: A Survey

By Pavan K. Turaga, Ramalingam Chellappa, Venkatramanan Siva Subrahmanian, Octavian Udrea. 2008

1,524 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

Delving into Egocentric Actions (2015, neutral): “Despite the tremendous effort on understanding actions in a surveillance setting [1] [35], it remains unclear whether previous methods for action recognition can be successfully applied to egocentric videos.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “For example, Wan et al. (2016a) proposed the novel spatial-temporal features for one-shot learning gesture recognition and have got promising performances on Chalearn Gesture Dataset CGD) (Guyon et al.”
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks (2017, background): “Traditionally, the community has focused on activity recognition in the domain of RGB videos [34, 13].”
Temporal Segment Networks for Action Recognition in Videos (2017, background): “Action recognition has been studied extensively in recent years and readers can refer to [34], [35], [36] for good surveys.”
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living (2012, methodology): “[118] distinguish between actions and activities by defining that”
4-dimensional local spatio-temporal features for human activity recognition (2011, background): “Although most previous work on feature extraction focused on using 2D videos [2], several approaches to extract features from 3D videos have been proposed in the past few years.”
Going deeper into action recognition: A survey (2016, background): “• Turaga et al. (2008) deﬁne action as “simple motion patterns usually executed by a single person and typically lasting for a very short duration (Order of tens of seconds).””
A survey on still image based human action recognition (2014, background): “It focuses on identifying a person's action or behavior from a single image.”
A Review of Human Activity Recognition Methods (2015, methodology): “Xu et al. (2015) addressed these limitations and proposed a general probabilistic framework for joint actor-action understanding while they presented a new dataset for actor-action recognition.”
Modeling Actions through State Changes (2013, background): “Action recognition has been the subject to a large body of work in computer vision [15, 24].”
Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations (2010, methodology): “One way is using cameras to visually detect people’s motion [8, 7].”
Survey on Fall Detection and Fall Prevention Using Wearable and External Sensors (2014, methodology): “The dataset is usually split and one part is used for training and the rest for testing [20].”
High-level event recognition in unconstrained videos (2012, background): “Ryoo, [111] Poppe and [139] Turaga et al.”
A Review on Video-Based Human Activity Recognition (2013, background): “[92] focus on the recognition of actions and activities and not on the lower-level processing modules such as detection and tracking.”
Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions (2013, neutral): “Human action and activity recognition is a broad and active area of research in computer vision, and comprehensive reviews of the proposed methods can be found in [42], [48].”
Driver-Activity Recognition in the Context of Conditionally Autonomous Driving (2015, background): “Also, human activity recognition is at the focus of research in the field of computer vision [6].”