Script identification is a key step in document analysis and recognition in multilingual environments. This study proposed a new dataset for script identification algorithms, containing images of ancient documents in 12 different ethnic scripts, including Chinese script, Naxi Dongba script, Yi script, Shui script, Tangut script, ancient Zhuang script, ancient Buyi script, Tibetan script, Dai script, Chagatai script, Mongolian script, and Manchu script. Focusing on the high accuracy required for ancient script identification, this study proposed a method named multi-attention ghost pyramid fusion network (MAGPNet). MAGPNet consists of a feature extraction network, a channel feature pyramid, and a Multi-Headed Self-Attention Bottleneck Block. The feature extraction network utilizes lightweight convolutional modules and parameter-free attention modules to enhance MAGPNet's feature extraction capability while maintaining a lighter structure. The channel feature pyramid increases the model's robustness in processing ancient documents of different scales. The Multi-Headed Self-Attention Bottleneck Block, by introducing a Multi-Headed Self-Attention, focuses on effective features. Experiments demonstrate that MAGPNet achieves a 99.97% accuracy rate on the multilingual ancient document image script identification dataset, maintaining excellent classification performance across multiple datasets.

Abstract As a promising architecture of next‐generation network, software defined‐information centric network (SD‐ICN) inherits the advantages of software defined network (SDN) and information‐centric network (ICN) to enable flexible and fast content retrieval, especially in the current era of artificial intelligence. However, the existing researches mainly focus on a single respective in this field, which motivates in comprehensively providing a forward‐looking guidance and development direction for scholars and engineers. To this end, the latest developments of SD‐ICN is presented. First, the widely‐accepted concepts and impacts on traditional networks are introduced. Second, the shortcomings of SDN and ICN over conventional networks are respectively analyzed to illustrate the necessity of SD‐ICN. Third, based on extensive analysis and deep deliberation, a methodical taxonomy for existing combination studies is proposed. They are divided into SDN over ICN, ICN over SDN, and mutual immersive pattern. Fourth, the performances of three integration categories are compared and the limitations of related works are highlighted. Fifth, the maturity index from six development indicators are evaluated. Further, the maturity and practicality of these schemes are generalized. Based on the above studies and comparisons, the lessons learned by SDN and ICN developments are concluded. Finally, future research directions and opportunities are discussed for the readers.

External knowledge is vital to many natural language processing tasks. However, current end-to-end dialogue systems often struggle to interface knowledge bases(KBs) with response smoothly and effectively. In this paper, we convert the raw knowledge into relation knowledge and integrated knowledge and then incorporate them into end-to-end task-oriented dialogue systems. The relation knowledge extracted from knowledge triples is combined with dialogue history, aiming to enhance semantic inputs and support better language understanding. Integrated knowledge involves entities and relations by graph attention, assisting the model in generating informative responses. The experimental results on three public dialogue datasets show that our model improves over the previous state-of-the-art models in sentence fluency and informativeness.

Sequential recommendation (SR) has attracted much research attention in the past few years. Most existing attribute integrated SR models do not directly model the complex relations between items and categorical attributes, as well do not exploit the power of attribute sequence in predicting the next item. In this paper, we propose an Item Categorical Attribute Integrated Sequential Recommendation (ICAI-SR) framework, which consists of an Item-Attribute Aggregation (IAA) model and Entity Sequential (ES) models. In IAA model, we employ a heterogeneous graph to represent the complex relations between items and different types of categorical attributes, then the attention mechanism based neighborhood aggregation is designed to model the correlations between items and attributes. For ES models, there are one Item Sequential (IS) model and one or more Attribute Sequential (AS) models. With IS and AS models, not only the item sequence but also the attribute sequence are used to predict the next item during model training. ICAI-SR is instantiated by taking Gated Recurrent Unit (GRU) and Bidirectional Encoder Representations from Transformers (BERT) as ES models, resulting in ICAI-GRU and ICAI-BERT respectively. Extensive experiments have been conducted on three public datasets to validate the performance of ICAI-SR. Experimental Results show that ICAI-SR performs better than both basic SR models and a competitive attribute integrated SR model.

Existing network embedding models regard all the links in a network as normal and model them without distinction. In real networks, there may be anomalous links like noise or adversarial links. We explicitly consider the existence of anomalous links in a network and propose anomaly aware network embedding (AANE) model. The key of AANE is the design of a new loss, which consists of anomaly aware loss and adjusted fitting loss. We adopt an anomaly indicator to iteratively select significant anomalous links from the network during model training, and removal loss and deviation loss are designed to model the reconstruction errors of selected anomalous and normal links respectively. To instantiate AANE, AAGAE and AAGCN are implemented on graph auto-encoder (GAE) and graph convolution based auto-encoder (GCNAE) respectively. For the purpose of evaluation, a heuristic anomalous link generation algorithm is proposed and by using the algorithm we generate anomalous links into six real world network datasets. Experimental results show that AANE outperforms both basic and competitive network embedding models in terms of anomalous link detection performance in most cases.

Binary descriptors are increasingly popular such as BRIEF, ORB, and BRISK. Typically, binary descriptors are computed by comparing pairs of image pixel intensities over a sampling pattern. To improve matching performance, lots of progresses have been made on the selection of pixel pairs, yet the discriminative power of pixel pairs is not fully studied.

Surveillance video privacy protection has drawn significant attention recently. In this paper, we describe a privacy protected video surveillance system which utilizes the emerging compressive sensing (CS) theory. Privacy regions are scrambled through block based CS sampling on quantized coefficients during compression. Security is ensured by key controlled chaotic sequence which is used to construct CS measurement matrix. To prevent drift error caused by scrambling, a coding restricted scheme is exploited. Experimental results show that the proposed system effectively protects privacy with the scene intelligible. Compared with the existing ones, this system has high security and dramatic coding efficiency improvement.

Scrambling is widely used to protect privacy in surveillance video. However, as a critical issue in privacy protected video scrambling, drift error has not been adequately studied. In this paper, we focus on drift error prevention for different elements scrambling in privacy protected H.264/AVC video, which is the prevailing coding standard. A restricted coding scheme is proposed to prevent drift error in Transform Coefficient (TC), Intra Prediction Mode (IPM) and Motion Vector (MV) scrambling, respectively. Experiments show that the proposed scheme effectively prevents drift error with coding efficiency dramatically improved.

Video encryption plays an important role in data security guarantee, which is increasingly important with the development of multimedia technology. A great deal of effort has been made in recent years to develop video encryption methods. However, few studies focus on visual security evaluation, which has significant impact in measuring the effectiveness of these methods. In this paper, a new metric for video encryption is proposed, which evaluates visual security based on color and edge features of original and cipher-videos. The metric is easy to be incorporated into video encryption system for visual security based encryption decision. In addition, subjective tests for visual security assessment have been fully carried out. Experiments show that the proposed metric had better correlation with subjective results than others.