Action classification on product manifolds

Lui, Yui Man; Beveridge, J. Ross; Kirby, Michael

doi:10.1109/cvpr.2010.5540131

Cited by 98 publications

(81 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are totally 599 videos. Similar to [16], a fixed position bounding box with a temporal window of 32 frames is selected, based on annotations by Lui [13]. Presumably, a smaller number of frames is sufficient [18].…”

Section: Resultsmentioning

confidence: 99%

Computation strategies for volume local binary patterns applied to action recognition

Baumann

Ehlers

Rosenhahn

et al. 2014

2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Volume Local Binary Patterns are a well-known feature type to describe object characteristics in the spatiotemporal domain. Apart from the computation of a binary pattern further steps are required to create a discriminative feature. In this paper we propose different computation methods for Volume Local Binary Patterns. These methods are evaluated in detail and the best strategy is shown. A Random Forest is used to find discriminative patterns. The proposed methods are applied to the well-known and publicly available KTH dataset and Weizman dataset for singleview action recognition and to the IXMAS dataset for multiview action recognition. Furthermore, a comparison of the proposed framework to state-of-the-art methods is given.

show abstract

Section: Resultsmentioning

confidence: 99%

Computation strategies for volume local binary patterns applied to action recognition

Baumann

Ehlers

Rosenhahn

et al. 2014

2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

show abstract

“…The KTH dataset consists of 599 videos. Similar to [28], a fixed position bounding box with a temporal window of 24 frames is selected, based on annotations by Lui [29]. Presumably, a smaller number of frames is sufficient [30].…”

Section: Datasetsmentioning

confidence: 99%

Thresholding a Random Forest Classifier

Baumann

Ehlers

et al. 2014

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. The original Random Forest derives the final result with respect to the number of leaf nodes voted for the corresponding class. Each leaf node is treated equally and the class with the most number of votes wins. Certain leaf nodes in the topology have better classification accuracies and others often lead to a wrong decision. Also the performance of the forest for different classes differs due to uneven class proportions. In this work, a novel voting mechanism is introduced: each leaf node has an individual weight. The final decision is not determined by majority voting but rather by a linear combination of individual weights leading to a better and more robust decision. This method is inspired by the construction of a strong classifier using a linear combination of small rules of thumb (AdaBoost). Small fluctuations which are caused by the use of binary decision trees are better balanced. Experimental results on several datasets for object recognition and action recognition demonstrate that our method successfully improves the classification accuracy of the original Random Forest algorithm.

show abstract

“…The method is derived from his CVPR 2010 paper [6]. It characterizes action videos as elements on a product manifold through High-Order Singular Value Decomposition (HOSVD) and employs geodesic distance for classification.…”

Section: Algorithms Employedmentioning

confidence: 99%

ChaLearn gesture challenge: Design and first results

Guyon¹,

Athitsos

Jangyodsuk

et al. 2012

2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

We organized a challenge on gesture recognition: http://gesture.chalearn.org. We made available a large database of 50,000 hand and arm gestures videorecorded with a Kinect T M camera providing both RGB and depth images. We used the Kaggle platform to automate submissions and entry evaluation. The focus of the challenge is on "one-shot-learning", which means training gesture classifiers from a single video clip example of each gesture. The data are split into subtasks, each using a small vocabulary of 8 to 12 gestures, related to a particular application domain: hand signals used by divers, finger codes to represent numerals, signals used by referees, marchalling signals to guide vehicles or aircrafts, etc. We limited the problem to single users for each task and to the recognition of short sequences of gestures punctuated by returning the hands to a resting position. This situation is encountered in computer interface applications, including robotics, education, and gaming. The challenge setting fosters progress in transfer learning by providing for training a large number of subtasks related to, but different from the tasks on which the competitors are tested.

show abstract

Action classification on product manifolds

Cited by 98 publications

References 19 publications

Computation strategies for volume local binary patterns applied to action recognition

Computation strategies for volume local binary patterns applied to action recognition

Thresholding a Random Forest Classifier

ChaLearn gesture challenge: Design and first results

Contact Info

Product

Resources

About