2015/12/12 by Guy Lev, Lev, Guy, Gil Sadeh +5 · 1 citation
Computer Science · #Generative Adversarial Networks and Image Synthesis #Human Pose and Action Recognition #Neural Networks and Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.1512.03958
arxiv created 2015/12/12 · arxiv updated 2015/12/15
Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences. We demonstrate that RNNs can be effectively used in order to encode sequences and provide effective representations. The methodology we use is based on Fisher Vectors, where the RNNs are the generative probabilistic models and the partial derivatives are computed using backpropagation. State of the art results are obtained in two central but distant tasks, which both rely on sequences: video action recognition and image annotation. We also show a surprising transfer learning result from the task of image annotation to the task of video action recognition.