RESUMEN
A diode-end-pumped simultaneously Q-switched and modelocked self-Raman YVO(4)/Nd:YVO(4)/YVO(4) laser at first-Stokes wavelength of 1175.9 nm was demonstrated. The shortest mode-locked pulse width of the laser was obtained to be ~23.57 ps, with the corresponding timebandwidth product of ~0.51. The maximum average output power, the highest pulse energy and the highest peak power were obtained to be 1.83 W, 6.1 µJ and 220 kW, respectively. The nonlinear Raman process improved the Q-switched mode-locking performance of the Stokes pulses.
RESUMEN
A rich video data representation can be realized by means of spatio-temporal frequency analysis. In this research study we show that a video can be disentangled, following the learning of video characteristics according to their spatio-temporal properties, into two complementary information components, dubbed Busy and Quiet. The Busy information characterizes the boundaries of moving regions, moving objects, or regions of change in movement. Meanwhile, the Quiet information encodes global smooth spatio-temporal structures defined by substantial redundancy. We design a trainable Motion Band-Pass Module (MBPM) for separating Busy and Quiet-defined information, in raw video data. We model a Busy-Quiet Net (BQN) by embedding the MBPM into a two-pathway CNN architecture. The efficiency of BQN is determined by avoiding redundancy in the feature spaces defined by the two pathways. While one pathway processes the Busy features, the other processes Quiet features at lower spatio-temporal resolutions reducing both memory and computational costs. Through experiments we show that the proposed MBPM can be used as a plug-in module in various CNN backbone architectures, significantly boosting their performance. The proposed BQN is shown to outperform many recent video models on Something-Something V1, Kinetics400, UCF101 and HMDB51 datasets.