HAck: A system for the recognition of human actions by kernels of visual strings

By Luc Brun, Gennaro Percannella, Alessia Saggese, Mario Vento. 2014

13 citations recorded by the source corpus.

In this paper we propose HAcK, a novel method for recognizing Human Actions by string Kernel; the main idea is to represent each action through a sequence of visual characters, namely a string, able to model the temporal evolution of the events. Visual characters are extracted by analyzing global descriptors of the scene and by taking advantage on the depth information provided by a Kinect sensor. The similarity between actions is evaluated with a fast global alignment kernel, which allows to deal with actions of different length as well as with the noise introduced during the features extraction step. HAcK has been evaluated over two standard datasets and the obtained results, compared with state of the art approaches, confirm its effectiveness and its applicability in real environments.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

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

1. Mario Vento
2. Alessia Saggese
3. Luc Brun
4. Pasquale Foggia
5. Horst Bunke
6. Kaspar Riesen

In Human-Computer Interaction

1. Luc Brun
2. Mario Vento
3. Pasquale Foggia
4. Alessia Saggese

Citations in the corpus

• Recognition of Human Actions using Edit Distance on Aclet Strings (2015, background): “…Source Accuracy HARED Proposed 85.2 Cuboids (Dollar et al., 2005) 74.4 Reject (Carletti et al., 2013) 79.8 Bow (Foggia et al., 2013) 84.1 HAcK (Brun et al., 2014) 80.1 Deep (Foggia et al., 2014) 84.7 both the datasets the performance achieved are very stable with respect to the number of the…”