Video object detection is more challenging than image object detection because of the deteriorated frame quality. To enhance the feature representation, state-of-the-art methods propagate temporal information into the deteriorated frame by aligning and aggregating entire feature maps from multiple nearby frames. However, restricted by feature map's low storage-efficiency and vulnerable contentaddress allocation, long-term temporal information is not fully stressed by these methods. In this work, we propose the first object guided external memory network for online video object detection. Storage-efficiency is handled by object guided hard-attention to selectively store valuable features, and long-term information is protected when stored in an addressable external data matrix. A set of read/write operations are designed to accurately propagate/allocate and delete multi-level memory feature under object guidance. We evaluate our method on the ImageNet VID dataset and achieve state-of-the-art performance as well as good speedaccuracy tradeoff. Furthermore, by visualizing the external memory, we show the detailed object-level reasoning process across frames.

No abstract

In a contemporary data center, Linux applications often generate a large quantity of real-time system call traces, which are not suitable for traditional host-based intrusion detection systems deployed on every single host. Training data mining models with system calls on a single host that has static computing and storage capacity is time-consuming, and intermediate datasets are not capable of being efficiently handled. It is cumbersome for the maintenance and updating of host-based intrusion detection systems (HIDS) installed on every physical or virtual host, and comprehensive system call analysis can hardly be performed to detect complex and distributed attacks among multiple hosts. Considering these limitations of current system-call-based HIDS, in this article, we provide a review of the development of system-call-based HIDS and future research trends. Algorithms and techniques relevant to system-call-based HIDS are investigated, including feature extraction methods and various data mining algorithms. The HIDS dataset issues are discussed, including currently available datasets with system calls and approaches for researchers to generate new datasets. The application of system-call-based HIDS on current embedded systems is studied, and related works are investigated. Finally, future research trends are forecast regarding three aspects, namely, the reduction of the false-positive rate, the improvement of detection efficiency, and the enhancement of collaborative security.

With the rapid growth of video data, video summarization technique plays a key role in reducing people's efforts to explore the content of videos by generating concise but informative summaries. Though supervised video summarization approaches have been well studied and achieved state-of-the-art performance, unsupervised methods are still highly demanded due to the intrinsic difficulty of obtaining high-quality annotations. In this paper, we propose a novel yet simple unsupervised video summarization method with attentive conditional Generative Adversarial Networks (GANs). Firstly, we build our framework upon Generative Adversarial Networks in an unsupervised manner. Specifically, the generator produces high-level weighted frame features and predicts frame-level importance scores, while the discriminator tries to distinguish between weighted frame features and raw frame features. Furthermore, we utilize a conditional feature selector to guide GAN model to focus on more important temporal regions of the whole video frames. Secondly, we are the first to introduce the frame-level multi-head self-attention for video summarization, which learns long-range temporal dependencies along the whole video sequence and overcomes the local constraints of recurrent units, e.g., LSTMs. Extensive evaluations on two datasets, SumMe and TVSum, show that our proposed framework surpasses state-of-the-art unsupervised methods by a large margin, and even outperforms most of the supervised methods. Additionally, we also conduct the ablation study to unveil the influence of each component and parameter settings in our framework. CCS CONCEPTS • Computing methodologies → Artificial intelligence.

Rapid state control of quantum systems is significant in reducing the influence of relaxation or decoherence caused by the environment and enhancing the capability in dealing with uncertainties in the model and control process. Bang-bang Lyapunov control can speed up the control process, but cannot guarantee convergence to a target state. This paper proposes two classes of new Lyapunov control methods that can achieve rapidly convergent control for quantum states. One class is switching Lyapunov control where the control law is designed by switching between bang-bang Lyapunov control and standard Lyapunov control. The other class is approximate bang-bang Lyapunov control where we propose two special control functions which are continuously differentiable and yet have a bang-bang type property. Related stability results are given and a construction method for the degrees of freedom in the Lyapunov function is presented to guarantee rapid convergence to a target eigenstate being isolated in the invariant set. Several numerical examples demonstrate that the proposed methods can achieve improved performance for rapid state control of quantum systems.