Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin

By Yang Wang, Greg Mori. 2011

210 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Actions ~ Transformations (2015, background): “Mid- to high-level representation are also used to model complex actions [41, 55, 36, 60, 14, 24].”
Videos as Space-Time Region Graphs (2018, background): “ng and action recognition. However, most of the early work has focused on using spatio-temporal appearance features. For example, a large eort has been spent on manually designing the video features [22,23,24,25,26,27,28,29,30,31]. Some of the hand-designed features such as the Improved Dense Trajec”
Human Action Recognition and Prediction: A Survey (2018, methodology): “In [91], [122], a part is considered as a hidden variable in their models.”
Discovering discriminative action parts from mid-level video representations (2012, methodology): “In particular, our model combines ideas from partbased models [33, 32, 9] with the extraction of a sparse, low-level video representation.”
Action Recognition by Hierarchical Sequence Summarization (2013, methodology): “[27] applied the max-margin learning criterion to train HCRFs.”
Latent Hierarchical Model of Temporal Structure for Complex Activity Classification (2014, methodology): “Probabilistic graphical models were usually adopted to model the temporal structure of human activity or motion trajectories, such as Hidden Markov Models (HMMs) [5], [9], Hidden Conditional Random Fields (HCRFs) [10], [11], and Dynamic Bayesian Networks (DBNs) [4], [34].”
Activity representation with motion hierarchies (2013, methodology): “Discriminative alternatives to these generative models, e.g. , [Bilen et al, 2011, Liu et al, 2011, Niebles et al, 2010, Raptis et al, 2012, Tang et al, 2012, Wang and Mori, 2011], often use techniques related to the popular deformable part model of Felzenszwalb et al [2010].”
Rank Pooling for Action Recognition (2015, background): “Since the ranking machines act on frame content, they actually capture both the appearance and their evolution over time.”
Learning latent spatio-temporal compositional model for human action recognition (2013, methodology): “To address complex actions with cluttered background, several compositional or expressive models were proposed and achieve very impressive results [24, 5, 28, 39, 13, 6].”
Multiple/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning (2015, methodology): “In our experiment, we compared the proposed method against two representative part-based methods, 2-D part model [40] and 3-D part model [34].”
Depth Induced Feature Representation for 4D Human Activity Recognition (2014, methodology): “Roughly, we divide activity recognition techniques into four categories, Bag-ofFeatures/SVM (BoF/SVM) approaches [17], Deformable Part Models (DPM) approaches[39], silhouette representation [3], [5], [14], [22], feature trajectories [38], [21], [23], [31].”
Understanding Indoor Scenes Using 3D Geometric Phrases (2013, background): “This formulation accommodates the uncertainty in associating an image to a parse graph G similarly to [8, 28]; i.”
View-Invariant Action Recognition Based on Artificial Neural Networks (2012, background): “The term elementary action refers to a single human action pattern.”
Pose Adaptive Motion Feature Pooling for Human Action Analysis (2014, methodology): “2011) and MMHCRF (Wang and Mori 2011), DeMoSegAction (Niebles et al.”
Video-Based Human Behavior Understanding: A Survey (2013, methodology): “Instead of analyzing the behavior of whole bodies, an alternative is to perform parts-based analysis [125], [126], where template matching is combined with a pictorial structure model to detect and localize actions.”