Learning deformable action templates from cluttered videos
By Benjamin Z. Yao, Song-Chun Zhu. 2009
77 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Cross-View Action Modeling, Learning, and Recognition (2014, background): “[23, 24] developed spatio-temporal AND-OR graph to model the spatiotemporal structure of the poses in an actions.”
- Learning Maximum Margin Temporal Warping for Action Recognition (2013, methodology): “Dynamic time warping (DTW) has been used to align videos for recognition [32], time series classification [13] and action retrieval [14].”
- Learning latent spatio-temporal compositional model for human action recognition (2013, background): “[40] proposed to generate spatio-template action templates with the information projection method.”
- Video Primal Sketch: A Unified Middle-Level Representation for Video (2015, methodology): “22, (b) is the action template given by the deformable action template model (Yao and Zhu (2009)) from the video shown in (a).”
- Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “as walking, jumping, and clapping, and to human-object interactions such as drinking and smoking [84, 85, 86, 87]; but most daily actions, such as opening a door, are defined by cause and effect (a door’s fluent changes from “closed” to “open,” regardless of how it is opened), rather than by the hum”
- Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data (2014, unknown): “The most similar model to our approach is temporal warping [22–25].”
- Joint action recognition and pose estimation from video (2015, methodology): “Many methods for action recognition bypass body poses and achieve promising results by using coarse/mid-level features for action classification on some datasets[6, 10, 26, 12, 18, 2, 33, 30].”