Search

For CNN-based visual action recognition, the accuracy may be increased if local key action regions are focused on. The task of self-attention is to focus on key features and ignore irrelevant information. So, self-attention is useful for action recognition. However, current self-attention methods usually ignore correlations among local feature vectors at spatial positions in CNN feature maps. In this paper, we propose an effective interaction-aware self-attention model which can extract information about the interactions between feature vectors to learn attention maps. Since the different layers in a network capture feature maps at different scales, we introduce a spatial pyramid with the feature maps at different layers for attention modeling. The multi-scale information is utilized to obtain more accurate attention scores. These attention scores are used to weight the local feature vectors of the feature maps and then calculate attentional feature maps. Since the number of feature maps input to the spatial pyramid attention layer is unrestricted, we easily extend this attention layer to a spatio-temporal version. Our model can be embedded in any general CNN to form a video-level end-to-end attention network for action recognition. Several methods are investigated to combine the RGB and flow streams to obtain accurate predictions of human actions. Experimental results show that our method achieves state-of-the-art results on the datasets UCF101, HMDB51, Kinetics-400, and untrimmed Charades. [ABSTRACT FROM AUTHOR]

With a fiber pigtailed electro-optic modulator as the active Q-switch, mode-hopping-free single-longitudinal-mode pulses are generated by a ring cavity fiber laser based on the injection seeding technique. The experimental results show that the single-longitudinal-mode oscillating properties of the laser may be determined by the power and the center frequency of the injection seed rather than the Q-switch waveform and modulation frequency. With the injected seed power of 200 μW, single-longitudinal-mode Q-switched pulses with the repetition rate and the pulse width from 1 to 100 kHz, and 50 to 400 ns are achieved with the laser. The output pulse linewidth can be narrowed effectively by reducing the coupling ratio of the output coupler of the laser. A stable single-longitudinal-mode pulse stream with a linewidth of 1.5 MHz is obtained with our laser, which may be the narrowest linewidth for a Q-switched fiber laser so far to our best knowledge. [ABSTRACT FROM PUBLISHER]