A combined pose, object, and feature model for action understanding

By Ben Packer, Kate Saenko, Daphne Koller. 2012

65 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

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 Control and Systems Engineering

Citations in the corpus

3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, methodology): “Several compositional approaches were studied for complex scenarios and achieved substantial progresses[33, 29, 39, 21, 23, 30, 4, 15], and they decomposed an activity into deformable parts and enriched the models with contextual information.”
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.”
What Actions are Needed for Understanding Human Actions in Videos? (2017, background): “With increasingly complex datasets such as UCF101 [33] and others [13, 18, 22, 8] came new challenges, including scale, background clutter, and action complexity, in turn leading to improved algorithms [37, 32, 23, 11].”
Generating Natural-Language Video Descriptions Using Text-Mined Knowledge (2013, methodology): “Proceedings of the NAACL HLT Workshop on Vision and Language (WVL ’13), pages 10–19, Atlanta, Georgia, 14 June 2013. c©2013 Association for Computational Linguistics”
A generative restricted Boltzmann machine based method for high-dimensional motion data modeling (2015, methodology): “Model-based methods include probabilistic graphical models such as Hidden Markov Models [5], Dynamic Bayesian Networks [16], Conditional Random Fields [17], and their variants.”
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.”
A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition (2015, methodology): “For activity recognition in RGB-D data, Packer et al. [31] employed the latent structural SVM to train the model with part-based pose trajectories and object manipulations.”
Modeling 4D Human-Object Interactions for Event and Object Recognition (2013, background): “In recent years, many work applied the human-object mutual context to event and object recognition [2, 5, 7, 9, 11, 14, 15, 23, 24].”
“Important stuff, everywhere!” Activity recognition with salient proto-objects as context (2014, unknown): “[23] rely on background subtraction in combination with articulated body tracking and assume that candidate objets are foreground regions that cannot be explained by limbs.”