Pose sentences: A new representation for action recognition using sequence of pose words

Recognizing human action from a far field of view

“…We evaluate the performance on each dataset by Method Accuracy (%) Our method 100 Fathi and Mori [9] 100 Blank et al [2] 99.6 Jhuang et al [15] 98.8 Hutan and Duygulu [11] 92.0 Table 1. Reported per-sequence accuracy on the Weizmann dataset.…”

“…The HOG descriptor was originally proposed for human detection [7]. Due to its robustness, HOG has been successfully applied in the problem of action recognition [11,16,17,21] and object recognition [4]. Similar to the gradient, optical flow is also a directional feature with magnitude.…”

A line based pose representation for human action recognition

“…Studies of Hatun et al [12], Ikizler et al [13,14] and Thurau et al [35], share a common property of employing histograms to represent the pose information in each frame. However, using histograms for pose representation results in the loss of geometrical information among the components (e.g.…”

“…Hatun et al [12] describe pose in each frame using the histogram of gradients (HOG) features obtained from radial partitioning of the frame. Similarly, Thurau et al [35] extend HOG based descriptor to represent pose primitives.…”

Example based video filters

“…Influenced by the recent success of Histogram of Oriented Gradients(HoG) in human/object detection tasks [6,10], we represent each frame (pose) of an action with a HoG descriptor.…”