Qing Lei

Learn More
The majority of methods for recognizing human actions are based on single-view video or multi-camera data. In this paper, we propose a novel multi-surface video analysis strategy. The video can be expressed as three-surface motion feature (3SMF) and spatio-temporal interest feature. 3SMF is extracted from the motion history image in three different video(More)
METHODS A 63-year-old woman with atrial fibrillation presented clinical symptoms and signs of acute ischemia in the right lower extremity on the 17th postoperative day after revision total hip arthroplasty of the left hip for aseptic loosening of femoral component. Aspirin was discontinued 7 days before surgery. Both computed tomography angiography and(More)
—This paper explores how to improve BOW model for human action recognition in real environment. Traditional codebook learning uses single appearance based local features, thus spatial and temporal correlations of local features are ignored. This leads to a considerable amount of mismatch between sample vectors and noisy visual words resulted from background(More)