Visual perception of biological motion and a model for its analysis

By G. Johansson. 1973

Subfields: Neuroscience, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, background): “Biological observations suggest that humans can recognize actions from just the motion of a few light displays attached to the human body (Johansson 1973).”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “The concept of skeleton-based representation can be traced back to the early seminal research of Johansson [35], which”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, background): “The biological studies [5] demonstrate that skeleton data”
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, background): “It has in fact been proved by Johansson [17] that the displacement of light sources located on keypoints on the humans’ skeleton are enough for the visual system to recognizing the displayed action (such as walking, Fig.”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “Humans can recognize actions with a few spots describing motions of the main joints of skeletons [24], and experiments show that a large set of actions can be recognized solely from skeletons [25].”
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks (2017, background): “Even without the context information and visual cues, early work [17] in biological perception and more recent methods [9, 10, 31] provide strong evidence that encoding humans as a 3D skeleton yields both a discriminative and a robust representation for activity analysis.”
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (2016, background): “Fortunately, biological observations from the early seminal work of Johansson suggest that the positions of a small number of joints can effectively represent human behavior even without appearance information (Johansson 1973).”
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets (2016, background): “In effect, as noticed long ago, body poses are highly informative to discriminate among human actions [13].”
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (2016, background): “A temporal evolution of the human skeleton is very informative for action recognition as shown by Johansson in his seminal experiment involving the moving lights display [13].”
A Biologically Inspired System for Action Recognition (2007, methodology): “been tested on simple artificial stimuli such as point-light motion stimuli [ 27 ].”
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (2019, background): “[9] have given an empirical and theoretical basis that key joints can provide highly effective information about human motion.”
Biological movements look uniform: evidence of motor-perceptual interactions. (1992, background): “For instance, it is known that gait (Beardworth & Bukner, 1981; Cutting, 1981; Cutting & Proffitt, 1981; Johansson, 1973) and other biomechanical patterns such as dancing (Johansson, 1973) can be recognized reliably even when they are described visually in the most succinct way.”
Attention Routines and the Architecture of Selection (2004, background): “The recognition of characteristic motions is so robust that a human form is rapidly recognized from the motions of a set of lights attached to a person filmed while walking, running, or performing push-ups in the dark (Johansson, 1973; Neri, Morrone, & Burr, 1998).”
Emotion Perception from Dynamic and Static Body Expressions in Point-Light and Full-Light Displays (2004, methodology): “4 Implications for the PL technique It is generally regarded that the PL technique for the study of biological motion eliminates or at least substantially reduces static form information (Johansson 1973).”
A unifying computational framework for motor control and social interaction. (2003, background): “The use of our own motor system in understanding actions could underlie our extraordinary ability to detect and identify biological motion ( Johansson 1973).”
RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos (2017, background): “Alternatively, human poses have proven useful for action recognition [14, 15, 17, 25, 40].”