Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions

By Yang Yang, Imran Saleemi, Mubarak Shah. 2013

128 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Unsupervised Learning of Long-Term Motion Dynamics for Videos (2017, methodology): “Another stream of work uses probabilistic graphical models such as Hidden Markov Models (HMM) [49], Conditional Random Fields (CRF) [12] or Latent Dialect Allocation (LDA) [45] to capture spatial-temporal structures and learn the relations in activities from RGB-D videos.”
Video Action Detection with Relational Dynamic-Poselets (2014, background): “Previous studies have shown that pose [23,13,10,17,7] and motion [27,30,15,5] are key elements in understanding human actions from videos.”
DistInit: Learning Video Representations Without a Single Labeled Video (2019, background): “What are the “right” labels for a video? Previous work tends to manually defines action ontologies in a top-down fashion [25, 28, 46] or else discovers classes from bottomup clustering [12, 57].”
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos (2020, background): “Closely related is also the clustering of spatio-temporal motion patterns for action recognition [46] andNayak’s work on iterated conditional modes [47] to extract signs from continuous sentences.”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, methodology): “[57], [58], [88], [124], Gaussian mixture models [31], [82], [109], [122], and random forests [143] are some of the paradigms explored.”
Online human gesture recognition from motion data streams (2013, unknown): “Most existing approaches [10, 14, 33, 35, 37] are about”
Watch-n-patch: Unsupervised understanding of actions and relations (2015, background): “Yang et al. [43] develop a meaningful representation by discovering local motion primitives in an unsupervised way, then a HMM is learned over these primitives.”
Going deeper into action recognition: A survey (2016, background): “ss et al.(2012) Motion Interchange Patterns 29.2 68.5 General 26.9 Sadanand and Corso(2012) Video Wise 76.4 Group Wise 57.9 Oneata et al. (2013) MBH + SIFT + Sqrt + L2 Normalization 54.8 90 63.3 82.1 Yang et al. (2013) 88 Without Human Detector 55.9 90.5 63 90.2 Wang and Schmid(2013) With Human Dete”
A Review of Human Activity Recognition Methods (2015, background): “Frontiers in Robotics and AI | www.frontiersin.org November 2015 | Volume 2 | Article 287 Yang et al. (2013) proposed anunsupervisedmethod for recognizing motion primitives for human action classification from a set of very few examples.”
Dense Procedure Captioning in Narrated Instructional Videos (2019, background): “Previous works on video understanding tend to recognize actions in video clips by detecting pose (Wang et al., 2013a; Packer et al., 2012) and motion (Wang et al., 2013b; Yang et al., 2013) or both (Wang et al., 2014) and ﬁne-grained features(Rohrbach et al., 2016).”