Joint Action Segmentation and Classification by an Extended Hidden Markov Model

Borzeshi, Ehsan Zare; Perez‐Concha, Oscar; Xu, Richard Yi Da; Piccardi, Massimo

doi:10.1109/lsp.2013.2284196

Cited by 21 publications

(42 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two methods [4,19] have been applied to realistic multi-action datasets. Hoai et al [19] deal with the dual problem of human action segmentation and classification.…”

Section: Multi-action Recognitionmentioning

confidence: 99%

“…2 for an example. The dataset was divided into two sets as in [4,8]: one for training and one for testing. In total, 64 and 36 multi-action videos were used for training and testing, respectively.…”

Section: Datasetsmentioning

confidence: 99%

“…This dataset has occlusions, a cluttered background, and many distractors such as objects being deliberately moved. For our experiments we have used the same subset as per [4], which contains 12 subjects making brownies. The subjects were asked to make brownies in a natural way (no instructions were given).…”

Section: Datasetsmentioning

confidence: 99%

“…To the best of our knowledge, the combination of probabilistic integration with Fisher vectors is novel for the multi-action segmentation and recognition problem. In contrast to [4,19,9], the proposed system requires fewer parameters to be optimised. We also avoid the need for a custom dynamic programming definition as in [19,9].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors

Carvajal¹,

McCool²,

Lovell³

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We propose a hierarchical approach to multi-action recognition that performs joint classification and segmentation. A given video (containing several consecutive actions) is processed via a sequence of overlapping temporal windows. Each frame in a temporal window is represented through selective lowlevel spatio-temporal features which efficiently capture relevant local dynamics. Features from each window are represented as a Fisher vector, which captures first and second order statistics. Instead of directly classifying each Fisher vector, it is converted into a vector of class probabilities. The final classification decision for each frame is then obtained by integrating the class probabilities at the frame level, which exploits the overlapping of the temporal windows. Experiments were performed on two datasets: s-KTH (a stitched version of the KTH dataset to simulate multi-actions), and the challenging CMU-MMAC dataset. On s-KTH, the proposed approach achieves an accuracy of 85.0%, significantly outperforming two recent approaches based on GMMs and HMMs which obtained 78.3% and 71.2%, respectively. On CMU-MMAC, the proposed approach achieves an accuracy of 40.9%, outperforming the GMM and HMM approaches which obtained 33.7% and 38.4%, respectively. Furthermore, the proposed system is on average 40 times faster than the GMM based approach.

show abstract

“…Two methods [4,19] have been applied to realistic multi-action datasets. Hoai et al [19] deal with the dual problem of human action segmentation and classification.…”

Section: Multi-action Recognitionmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors

Carvajal¹,

McCool²,

Lovell³

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Sequential labeling has been drawing increasing attention from the image processing and machine learning communities [1,2,3,4,5]. Also known as tagging, or decoding, sequential labeling consists of the assignment of a sequence of class labels to a sequence of measurements.…”

Section: Introductionmentioning

confidence: 99%