CHAR Learn冠军方案

1.      CHALEARN冠军方案⁹

1.1.      Large-scalegesture recognition based on multimodaldata with C3D and TSN.

  Retivex做图像enhancement，mean filter做深度图enhancement。

   特征级联做分类。

1.2.      Learningboth Dynamic and Static Action Contextfor Gesture Recognition

  动态特征使用了rgb，d，of，skeleton。

  静态特征使用了rank pooling。

1.3.      SimpleTrick: Masked C3D for Isolated Sign Language Recognition

只提取了手

1.4.      Large-scaleIsolated Gesture Recognition Using HeterogeneousNetworks

1.5.      Large-ScaleIsolated Gesture Recognition using 3DCNNand Convolutional LSTM

Reference

9.     ChaLearn.Available at: http://chalearnlap.cvc.uab.es/challenge/25/track/23/result/.(Accessed: 22nd September 2017)