Dynamic scene classification on portable platforms is extremely challenging due to the contradiction between model complexity and computing resources. To resolve this long-standing dilemma, we propose the compressed attentive multi-granularity network (CAM-Net) in a two-step manner. First, we present a novel AM-Net based on multi-granularity attention units to boost the performance of the full-precision model. It captures and enhances both coarse and fine target-related information. Then, we introduce an efficient binary approximation to AM-Net to improve computing efficiency, leading to CAM-Net. Particularly, a grouping guidance approach is adopted to guide the reconstruction of full-precision weights from binary ones. With this guidance, CAM-Net can significantly reduce memory usage as well as CPU consumption, yet only cause a slight decline in accuracy. Extensive experiments have been conducted on three benchmark datasets, i.e., Maryland, YUPENN ++ and ActivityNet, demonstrating the effectiveness and superiority of the proposed method on scene classification.

Dynamic scene classification is an important yet challenging problem especially with the presence of defected or irrelevant frames due to unconstrained imaging conditions such as illumination, camera motion and irrelevant background. In this paper, we propose the attentive temporal pyramid network (ATP-Net) to establish effective representations of dynamic scenes by extracting and aggregating the most informative and discriminative features. The proposed ATP-Net detects informative features of frames that contain the most relevant information to scenes by a temporal pyramid structure with the incorporated attention mechanism. These frame features are effectively fused by a newly designed kernel aggregation layer based on kernel approximation into a discriminative holistic representations of dynamic scenes. The proposed ATP-Net leverages the strength of attention mechanism to select the most relevant frame features and the ability of kernels to achieve optimal feature fusion for discriminative representations of dynamic scenes. Extensive experiments and comparisons are conducted on three benchmark datasets and the results show our superiority over the state-of-the-art methods on all these three benchmark datasets.

Dynamic scene classification has been extensively studied in computer vision due to its widespread applications. The key to dynamic scene classification lies in jointly characterizing spatial appearance and temporal dynamics to achieve informative representation, which remains an outstanding task in the literature. In this paper, we propose a unified framework to extract spatial and temporal features for dynamic scene representation. More specifically, we deploy two variants of deep convolutional neural networks to encode spatial appearance and short-term dynamics into short-term deep features (STDF). Based on STDF, we propose using the autoregressive moving average model to extract long-term frequency features (LTFF). By combining STDF and LTFF, we establish the long-short-term feature (LSTF) representations of dynamic scenes. The LSTF characterizes both spatial and temporal patterns of dynamic scenes for comprehensive and information representation that enables more accurate classification. Extensive experiments on three-dynamic scene classification benchmarks have shown that the proposed LSTF achieves high performance and substantially surpasses the state-of-the-art methods.

A new approach to solving dynamic optimization problems (DOPs), called robust optimization over time (ROOT) has recently been suggested and a number of optimization algorithms for finding ROOT solutions have been developed. These algorithms typically rely on the predicted fitness in the new environment to determine the robustness of a solution, which may be considerably different from the true robustness due to the errors in fitness prediction. Consequently, performance comparison based on the predicted fitness may be also misleading. In this paper, we propose a new formulation of the performance measures for quantitatively evaluate the performance of optimization algorithms for finding robust solutions over time, assuming that the actual optimal solution of the problem is known. We empirically verify the proposed performance measures by analyzing the robust optimal solutions obtained in two recently reported ROOT evolutionary algorithms. Our results indicate that the proposed performance measures are able to provide an effective means for performance comparison of ROOT algorithms.