Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your…

By A. G. Ramm, Steven M. Matsuoka. 2005

Subfields: AI Ethics, Fairness & Society

How researchers see this paper

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

In AI Ethics, Fairness & Society

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Several earlier surveys were also published to review methods to recognize human poses, motions, gestures, and activities [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], as well as their applications [49], [50].”
Discriminative virtual views for cross-view action recognition (2012, background): “Opportunities for the use of action analysis in domains such as surveillance, video indexing/retrieval, and human-computer interaction are growing fast [16, 18, 1], but realizing this potential relies on the ability to accurately interpret human activities from a broad range of viewing directions.”
Efficient Human Pose Estimation from Single Depth Images (2013, background): “Human pose estimation has generated a vast literature, surveyed in [21], [22].”
Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data (2013, methodology): “Several methods produce a 3D mesh and/or kinematic skeleton as their output [13, 17].”
Social signal processing: Survey of an emerging domain (2009, background): “Also automatic posture recognition has been addressed in few works, mostly aiming at surveillance [57] and activity recognition [206] (See [54][116][153] for extensive overviews of the past work in the field).”
Efficient model-based 3D tracking of hand articulations using Kinect (2011, background): “One of its instances, the 3D tracking of human hands has a number of diverse applications [6, 14] including but not limited to human activity recognition, human-computer interaction, understanding human grasping, robot learning by demonstration, etc.”
Understanding egocentric activities (2011, background): “Action and activity recognition have been the subject of a vast amount of research in computer vision literature [22, 32].”
VNect (2017, methodology): “video [Moeslund et al. 2006], with recent solutions being real-time [Stoll et al.”
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video (2015, background): “Considerable research has addressed the challenge of human motion capture from imagery [26, 41, 9, 33].”
Deliberation for autonomous robots: A survey (2017, methodology): “They have been successfully applied to movement tracking and gesture recognition [232, 149].”
Resolving 3D Human Pose Ambiguities With 3D Scene Constraints (2019, background): “Traditionally, human pose estimation methods [43] estimate bodies in isolation ignoring the surrounding world, while 3D reconstruction methods focus on acquiring the dense 3D shape of the scene only [76] or performing semantic analysis [7, 13, 54], assuming no humans are present.”
The Visual Object Tracking VOT2015 Challenge Results (2015, background): “Visual tracking is diverse research area that has attracted significant attention over the last fifteen years [20, 48, 18, 27, 49, 79, 43].”
A Review of Human Activity Recognition Methods (2015, background): “The survey of Moeslund et al. (2006) mainly focused on pose-based action recognition methods and proposed a fourfold taxonomy, including initialization of human motion, tracking, pose estimation, and recognition methods.”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, methodology): “We refer the reader to the surveys in [7] and [8] for more details about human detection in applications different other than PPSs.”
Bridging the Gap between Social Animal and Unsocial Machine: A Survey of Social Signal Processing (2012, unknown): “Similarly, fully naturalistic movements of virtual agents can be attained when human movements recorded using motion capture technology are played back [213], but movements generated based on behavior markup language [196] tend to look less natural [214].”
Cross-View Action Recognition from Temporal Self-similarities (2008, background): “Visual recognition and understanding of human actions has attracted much of attention over the past three decades [1,2] and remains an active research area of computer vision.”