Conditional models for contextual human motion recognition

By Cristian Sminchisescu, Atul Kanaujia, Dimitris N. Metaxas. 2006

386 citations recorded by the source corpus.

Subfields: 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, methodology): “The other is to explore temporal dependencies of the inter-frame content for action dynamics modeling, using hierarchical maximum entropy Markov model (Sung et al. 2011), hidden Markov model (Xia, Chen, and Aggarwal 2012) or Conditional Random Fields (Sminchisescu et al. 2005).”
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (2016, methodology): “The other is the modeling of temporal dynamics, such as Hidden Markov Model (Xia, Chen, and Aggarwal 2012), Conditional Random Fields (Sminchisescu, Kanaujia, and Metaxas 2006), and Recurrent Neural Networks (Du, Wang, and Wang 2015).”
Unstructured human activity detection from RGBD images (2011, methodology): “We have also made the dataset and code available open-source at: http://pr.cs.cornell.edu/humanactivities”
Featureweighting in dynamic timewarping for gesture recognition in depth data (2011, background): “Recently, there has been an emergent interest in Conditional Random Field (CRF) [12] for the learning of sequences .”
An end-to-end generative framework for video segmentation and recognition (2015, background): “Most early approaches for action recognition with structured temporal models relied on either motion capture data [8, 28] or hand-labeled trajectories [22].”
Poselet Key-Framing: A Model for Human Activity Recognition (2013, methodology): “Sequential models: Hidden semi-Markov Models (HSMM) [10] , CRFs [31], and finite-state-machines [13] have been used to model the temporal evolution of human activities.”
A generative restricted Boltzmann machine based method for high-dimensional motion data modeling (2015, background): “However, most models, such as hidden Markov model (HMM) [5], dynamic Bayesian network (DBN) [7] and conditional random field (CRF) [8] are time-slice local models, which assume Markov property and stationary transitions and hence can only capture local dynamics.”
Challenges in multimodal gesture recognition (2016, background): “In (Sminchisescu et al., 2006) it is proposed the first conditional/discriminative chain model for action recognition.”
Exemplar-based Action Recognition in Video (2009, background): “[4, 15, 19]) have been studied mostly, good results have been reported recently using extensions of traditional object recognition approaches to the spatio-temporal domain [5, 12, 16, 22].”
Learning Clip Representations for Skeleton-Based 3D Action Recognition (2018, methodology): “(HMMs) [19], [20], Conditional Random Fields (CRFs) [21] and Temporal Pyramids (TPs) [7], [22] have been used to”
Learning invariance through imitation (2011, background): “We seek to learn a functional mapping Zmi = f(Xmi |θ), parameterized by θ, such that if points Xmi and Xmj come from nearby seed images (i.e. |ymi −ymj | is small), then Zmi and Z m j will lie close-by in the output space.”
Human Activity Detection from RGBD Images (2011, methodology): “Sminchisescu et al. (2005) utilized conditional random ﬁelds and maximum-entropy Markov models for activity recognition, arguing that these models overcome some of the limitations presented by hidden Markov models.”
Conditional random fields for activity recognition (2007, background): “[2, 11, 14], while conditional random fields, a more recent model, are just now expanding outside of their original natural language processing context into a range of areas such as image processing [4], gesture recognition [13], motion tracking [10], and activity recognition [6].”
Hidden Conditional Random Fields (2007, methodology): “Sminchisescu [20] applied CRFs to classify human motion activity and demonstrated their model was more accurate than MEMMs.”
Learning Spatio-Temporal Structure from RGB-D Videos for Human Activity Detection and Anticipation (2013, methodology): “Frameworks such as HMMs (Hongeng & Nevatia, 2003; Natarajan & Nevatia, 2007), DBNs (Gong & Xiang, 2003), CRFs (Quattoni et al., 2007; Sminchisescu et al., 2005; Koppula et al., 2013), and semi-CRFs (Sarawagi & Cohen, 2004) have been previously used to model the temporal structure of videos and text.”