Search

Hand gesture recognition on the depth videos is a promising approach for automotive interfaces because it is less sensitive to light variation and more accurate than other traditional methods. However, video gestures recognition is still a challenging task since lots of interferences are induced by the uncorrelated gesture factors. Considering that if the displays are more relevant, the results will more accurate, so ResNext, a kind of compact and efficient neural network, is firstly used as feature extractor, then an improved weighted frame unification method is adopted to obtain the key frame samples, finally the Discriminant correlation analysis (DCA) is employed to fuse features for static data and dynamic data after conducting Feature embedding branch (FEB) on static data. The public dataset named Depth based gesture recognition database (DGRD) is used in this paper, but the dataset is a little small and the class distribution is largely imbalance, and we find the performance of ResNext degrades badly in the condition of imbalance problem although it achieves excellent result at sufficient training data. In order to conquer the disadvantages of limited dataset, a special loss function scheme combining the softmax loss and dice loss is proposed. Evaluation of the algorithm performances in comparison with other state-of-the-art methods indicates that the proposed method is more practical for gesture recognition and may be widely adopted by automotive interfaces.

Purpose: Locally recurrent, previously irradiated primary head and neck tumors have historically been associated with poor outcomes. Stereotactic body radiation therapy has emerged as a feasible and promising treatment option for tumor recurrence, particularly in nonsurgical candidates. This study aimed to assess the associated outcomes of stereotactic body radiation therapy used in this setting.Methods: Retrospective analysis of a prospectively collected database of 25 patients treated with CyberKnife for unresectable, recurrent head and neck cancer in a previously irradiated field. The primary end points evaluated were rates of survival, tumor control, and treatment-related toxicities.Results: Median survival of the study population was 7.5 months (range, 1.5-47.0 months). Median survival of the 20 (80%) patients who were treated with curative purpose was 8.3 months. One-year overall survival rate for the entire population was 32%. The respective 1-year and 2-year survival rates for the curative subcohort were 40% and 20%, respectively. Local and locoregional failure occurred in 8 (32%) and 7 (28%) patients, respectively. Low severe acute (4%) and late (6%) treatment-related toxicity rates were observed. No grade 4 or 5 toxicities were observed.Conclusion: Stereotactic body radiation therapy is a viable treatment option for patients with unresectable, recurrent head and neck cancer. Significant tumor control rates are achievable with minimal severe toxicity. Although perhaps associated with patient selection and a heterogeneous sample, overall survival of stereotactic body radiation therapy outcomes appears unfavorable.