Filter pruning is an important technique to compress convolutional neural networks (CNNs) to acquire light-weight high-performance model for practical deployment. However, the existing filter pruning methods suffer from sharp performance drops when the pruning ratio is large, probably due to the unrecoverable information loss caused by aggressive pruning. In this paper, we propose a dual attention based pruning approach called DualPrune to push the limit of network pruning at an ultra-high compression ratio. Firstly, it adopts a graph attention network (GAT) to automatically extract filter-level and layer-level features from CNNs based on the roles of their filters in the whole computation graph. Then the extracted comprehensive features are fed to a side-attention network, which generates sparse attention weights for individual filters to guide model pruning. To avoid layer collapse, the side-attention network adopts a side-path design to preserve the information flow going through the CNN model properly, which allows the CNN model to be pruned at a high compression ratio at initialization and trained from scratch afterward. Extensive experiments based on several well-known CNN models and real-world datasets show that the proposed DualPrune method outperforms the state-of-the-art methods with significant performance improvement, particularly for model compression at a high pruning ratio.

Sign languages are mainly expressed by human actions, such as arm, hand, and finger motions. Thus a skeleton which reflects human pose information can provide an important cue for distinguishing signs (i.e., human actions), and can be used for sign language translation (SLT), which aims to translate sign language to spoken language. However, the recent neural networks typically focus on extracting local-area or full-frame features, while ignoring informative skeleton features. Therefore, this paper proposes a novel skeleton-aware neural network, SANet, for vision-based SLT. Specifically, to introduce skeleton modality, we design a self-contained branch for skeleton extraction. To efficiently guide the feature extraction from videos with skeletons, we concatenate the skeleton channel and RGB channels of each frame for feature extraction. To distinguish the importance of clips (i.e., segmented short videos), we construct a skeleton-based graph convolutional network, GCN, for feature scaling, i.e., giving an importance weight for each clip. Finally, to generate spoken language from features, we provide an end-to-end method and a two-stage method for SLT. Besides, based on SANet, we provide an SLT solution on the smartphone for benefiting communication between hearing-impaired people and normal people. Extensive experiments on three public datasets and case studies in real scenarios demonstrate the effectiveness of our method, which outperforms existing methods.

In mobile social networks, next point-of-interest (POI) recommendation is a very important function that can provide personalized location-based services for mobile users. In this paper, we propose a recurrent neural network (RNN)-based next POI recommendation approach that considers both the location interests of similar users and contextual information (such as time, current location, and friends’ preferences). We develop a spatial-temporal topic model to describe users’ location interest, based on which we form comprehensive feature representations of user interests and contextual information. We propose a supervised RNN learning prediction model for next POI recommendation. Experiments based on real-world dataset verify the accuracy and efficiency of the proposed approach, and achieve best F1-score of 0.196 754 on the Gowalla dataset and 0.354 592 on the Brightkite dataset.