Joint pose estimation and action recognition in image graphs

Raja, K L Nirmal; Laptev, Ivan; Pérez, Patrick; Oisel, Lionel

doi:10.1109/icip.2011.6116197

Cited by 33 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Borzeshi et al [2] represent each frame as a graph with vertices corresponding to the spatial local features extracted from this frame. Raja et al [14] describe a person in a frame with a graphical model which contains six vertices encoding the positions of five body parts and the action label. Gaur et al [6] construct a string of feature graphs for the spatiotemporal layout of local features.…”

Section: Related Workmentioning

confidence: 99%

Human Action Recognition Based on Context-Dependent Graph Kernels

Yuan

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Graphs are a powerful tool to model structured objects, but it is nontrivial to measure the similarity between two graphs. In this paper, we construct a two-graph model to represent human actions by recording the spatial and temporal relationships among local features. We also propose a novel family of context-dependent graph kernels (CGKs) to measure similarity between graphs. First, local features are used as the vertices of the two-graph model and the relationships among local features in the intra-frames and inter-frames are characterized by the edges. Then, the proposed CGKs are applied to measure the similarity between actions represented by the two-graph model. Graphs can be decomposed into numbers of primary walk groups with different walk lengths and our CGKs are based on the context-dependent primary walk group matching. Taking advantage of the context information makes the correctly matched primary walk groups dominate in the CGKs and improves the performance of similarity measurement between graphs. Finally, a generalized multiple kernel learning algorithm with a proposed l12-norm regularization is applied to combine these CGKs optimally together and simultaneously train a set of action classifiers. We conduct a series of experiments on several public action datasets. Our approach achieves a comparable performance to the stateof-the-art approaches, which demonstrates the effectiveness of the two-graph model and the CGKs in recognizing human actions.

show abstract

Section: Related Workmentioning

confidence: 99%

Human Action Recognition Based on Context-Dependent Graph Kernels

Yuan

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Another trend of research is the development of pose-based approaches for better analysis of human actions. Methods of this category, e.g., [7,8], carry out pose estimation to detect body parts in each frame, and recognize actions by analyzing the motions of body parts. These methods rely on the high-quality estimation of poses, which is a difficult task even if a large amount of training data is provided.…”

Section: Related Workmentioning

confidence: 99%

Skeleton-augmented Human Action Understanding by Learning with Progressively Refined Data

Wei

Tang

Lin

et al. 2014

Proceedings of the 1st ACM International Workshop on Human Centered Event Understanding From Multimedia

View full text Add to dashboard Cite

With the aim at accurate action video retrieval, we firstly present an approach that can infer the implicit skeleton structure for a query action, an RGB video, and then propose to expand this query with the inferred skeleton for improving the performance of retrieval. It is inspired by the observation that skeleton structures can compactly and effectively represent human actions, and are helpful in bridging the semantic gap in action retrieval. The focal point is hence on action skeleton estimation in RGB videos. Specifically, an iterative training procedure is developed to select relevant training data for inferring the skeleton of an input action, since corrupt training data not only degrades performance but also complicates the learning process. Through the iterations, relevant training data are gradually revealed, while more accurate skeletons are inferred with the refined training set. The proposed approach is evaluated on ChaLearn 2013. Significant performance gains in action retrieval are achieved with the aid of the inferred skeletons.

show abstract

“…We seek to investigate the feasibility of using action detection to facilitate 3D human pose estimation in uncontrolled and monocular videos. Early approaches that combines action and pose constrains include [36] and [22]. The closest work to this idea is [34] that uses action recognition to assist a multiview 3D HPE algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Kim

Cipolla

2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

This work addresses the challenging problem of unconstrained 3D human pose estimation (HPE) from a novel perspective. Existing approaches struggle to operate in realistic applications, mainly due to their scene-dependent priors, such as background segmentation and multi-camera network, which restrict their use in unconstrained environments. We therfore present a framework which applies action detection and 2D pose estimation techniques to infer 3D poses in an unconstrained video. Action detection offers spatiotemporal priors to 3D human pose estimation by both recognising and localising actions in space-time. Instead of holistic features, e.g. silhouettes, we leverage the flexibility of deformable part model to detect 2D body parts as a feature to estimate 3D poses. A new unconstrained pose dataset has been collected to justify the feasibility of our method, which demonstrated promising results, significantly outperforming the relevant state-of-the-arts.

show abstract

Joint pose estimation and action recognition in image graphs

Cited by 33 publications

References 12 publications

Human Action Recognition Based on Context-Dependent Graph Kernels

Human Action Recognition Based on Context-Dependent Graph Kernels

Skeleton-augmented Human Action Understanding by Learning with Progressively Refined Data

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Contact Info

Product

Resources

About