The sketch-based image retrieval (SBIR) task has long been researched at the instance level, where both query sketches and candidate images are assumed to contain only one dominant object. This strong assumption constrains its application, especially with the increasingly popular intelligent terminals and human-computer interaction technology. In this work, a more general scene-level SBIR task is explored, where sketches and images can both contain multiple object instances. The new general task is extremely challenging due to several factors: (i) scene-level SBIR inherently shares sketch-specific difficulties with instance-level SBIR (e.g., sparsity, abstractness, and diversity), (ii) the cross-modal similarity is measured between two partially aligned domains (i.e., not all objects in images are drawn in scene sketches), and (iii) besides instance-level visual similarity, a more complex multi-dimensional scene-level feature matching problem is imposed (including appearance, semantics, layout, etc.). Addressing these challenges, a novel Conditional Graph Autoencoder model is proposed to deal with scene-level sketch-images retrieval. More importantly, the model can be trained with only pairwise supervision, which distinguishes our study from others in that elaborate instance-level annotations (for example, bounding boxes) are no longer required. Extensive experiments confirm the ability of our model to robustly retrieve multiple related objects at the scene level and exhibit superior performance beyond strong competitors.

Sketch-based image retrieval (SBIR) is an attractive research area where freehand sketches are used as queries to retrieve relevant images. Existing solutions have advanced the task to the challenging zero-shot setting (ZS-SBIR), where the trained models are tested on new classes without seen data. However, they are prone to overfitting under a realistic scenario when the test data includes both seen and unseen classes. In this paper, we study generalized ZS-SBIR (GZS-SBIR) and propose a novel semi-transductive learning paradigm. Transductive learning is performed on the image modality to explore the potential data distribution within unseen classes, and zero-shot learning is performed on the sketch modality sharing the learned knowledge through a semi-heterogeneous architecture. A hybrid metric learning strategy is proposed to establish semantics-aware ranking property and calibrate the joint embedding space. Extensive experiments are conducted on two large-scale benchmarks and four evaluation metrics. The results show that our method is superior over the state-of-the-art competitors in the challenging GZS-SBIR task.

Internet of Things (IoT) software is used to control the distributed hardware of the underlying network and provide a reliable operating platform for various services. In production system, diversity IoT software provides multiple services, flows of different software run in parallel on the same IoT platform. Thus, system-level network parameter configurations may not be suitable for all service needs. In this paper, we focus on the challenge of the personally parameterizing transmission unit size and congestion windows (CWND) in flow control. We propose deeper flow control software model (DeepFC) for finer-grained flow control than traditional algorithms. DeepFC consist of two parts: (i) Since system-level transmission unit size may degrade network performance due to frequent fragmentation, we combine path MTU (PMTU) and deep reinforcement learning (DRL) to predict fine-grained flow-level transmission unit size. (ii) Transmission unit size is related to CWND in flow control. The fine-grained transmission unit size needs fine-grained congestion control solution. In DeepFC, we consider the mutual coupling between transmission unit size and CWND parameter configuration to further improve network performance. Experimental results show that DeepFC can reduce fragmentation by 67.8% compared to the protocols with system-level transmission unit size, flow completion time can be reduced by 20.93%, and throughput can be increased by 19.96% compared to the average of benchmark algorithms.

Network anomaly detection provides a reliable and stable service to detect faults and prevent security attacks effectively. However, existing detection methods still encounter many challenges. The supervised learning method is unsuitable because the anomaly samples are seriously sparse and hard to label. Unsupervised learning, as a promising method, is widely used while the discriminative features are ignored when reconstructing from the normal feature space. This paper proposes a novel probability correlation learning based on autoencoder called PCDetect, a semi-supervised learning method. Since we assumed the anomaly samples deviate from the distribution of normal samples, approximating the distribution of original data is proposed as an efficient preprocessing methodology to capture the discriminative features. Moreover, an encoder-decoder neural network associated with the proposed loss function is designed to learn the low-dimensional feature representation from raw data and constrain the latent representation to follow different referenced distributions based on a few anomaly labels. In this way, The correlation of the referenced distribution and the reconstruction of latent representation will be used to quantify the probability of anomaly. Extensive experiments are conducted on two public real-world datasets, NSL-KDD and UNSW-NB15. Results show the proposed PCDetect can efficiently cope with the imbalance and high-dimensional issues compared with several popular supervised learning methods, significantly improve the accuracy, and reduce the false rate as a whole compared with unsupervised learning.

Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, Ming Liu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Face detection has achieved great success with the development of convolution neural network. However, it remains a challenging problem to detect small and blurred faces in unconstrained environment. This paper presents a novel cascade single-shot face detector, named Cascade Single Shot Face Detector (CSSD), which introduces novel cascade classification and regression network in an anchor-based face detector to reject false positives and improve location accuracy. We have contributed in the following three aspects: 1) proposing a feature enchanted and scale-invariable face detection architecture to process faces with different scales; 2) regressing bounding boxes of faces in two steps with a cascade method; 3) filtering negative anchors online after anchor refinement and rebalancing puzzle negative anchors and positive anchors with rate of 3:1. As a consequence, our method achieves state-of-the-art detection performance on FDDB and WIDER FACE dataset.

Multiple heterogenous virtual networks are given the ability to run on a shared infrastructure simultaneously as independent slices in the network virtualization environment. However, a major challenge is how to map multiple virtual networks, with specific node and link constraints, onto the shared substrate network, known as virtual network embedding problem. By taking topology attribute into account, topology-aware virtual network embedding algorithms efficiently improve the performance by leveraging a node ranking method based on Markov chain. However, as the basis of node ranking, the resource evaluation of node which is calculated as the product of its CPU and bandwidth may be incorrect. Moreover, a greedy matching strategy is always applied in the node mapping stage, which may lead to unnecessary bandwidth consumption by ignoring the relationships between the mapped substrate nodes and the mapping one. In this paper, we re-think the topology-aware virtual network embedding from a statistical perspective by proposing a statistical method to generate a dependency matrix representing the importance of every node and the relationships between every two nodes in the substrate network. Based on this dependency matrix, bayesian network analysis is leveraged to iteratively select the substrate node, with the closest relationship to the selected ones, to achieve node mapping process. Extensive simulations were conducted and the results show that our proposed algorithm has better performance in the long-term run.

Aligning different ontologies from similar (or same) domains is an active field of current research. There are various solutions which process and analyze lexical, structural or semantic information to align ontologies. However, there are few solutions that focus on interpreting the concepts that entities are presented with and using them in relation to the semantics implied in an ontology. In this paper, the prototype (OACLAI) is presented to tackle this by combining lexical analysis with consequences from reasoners which reflect the semantics implied in an ontology. We evaluate OACLAI over the four real ontologies and compare it against the seven solutions. The experiments show that the accuracy of OACLAI is higher than those of others on average.

Service composition constructs composite applications with different services to fulfill numerous service requirements. Different users have various QoS demands for composite services. In this paper, we present a service composition model considering not only multiple QoS constraints but also load balance factors. Moreover, a service selection algorithm based on niching technique and particle swarm optimization (PSO) is proposed for the service composition problem. It supports optimization problems with any kinds of constraints and objective functions. Simulation results show the proposed algorithm is effective and efficient for service composition under any circumstances.