4 pixels input per cycle 67 MHz maximum clock frequency on Xilinx Kintex-7 XC7K325 TFFV676-1 The throughput reaches 67 * 4 = 268 MPixels/s. The encoding frame rate for 1920x1152 video is 121 fps.

Abstract: We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, ...

Abstract: Change detection is a critical task in earth observation applications. Recently, deep-learning-based methods have shown promising performance and are quickly adopted in change detection.