The energy consumption of virtualized data centers has grown very fast in last several years. Because a large number of hosts are running in an idle state, virtualized data centers waste a large amount of electric ene...
详细信息
Knowledge Graphs have been practical tools to represent and integrate plentiful structural and semantic information in mainstream industrial scenarios. While promising, the heterogeneity and complexity of KGs pose a f...
详细信息
Video person re-identification is receiving academic interest. However, the practical application of the algorithm is hardly supported because of prohibitive annotated data. Hence, the study for unlabeled data will le...
Video person re-identification is receiving academic interest. However, the practical application of the algorithm is hardly supported because of prohibitive annotated data. Hence, the study for unlabeled data will lead to an attractive alternative. This work explores an innovative strategy, namely, learning to cluster unlabeled person in the video through graph convolutional networks. In this paper, we find that the possibility of inter-frame linkage can be inferred from context. Therefore, a pose-guided topology linkage clustering framework is proposed. Our framework consists of three modules: (i) a pose-guided representation module; (ii) a pose-guided embedding module; (iii) a link prediction module. Firstly, the representation coding alone is performed at the level of relational induction bias, embedding the implicit pose structure information in image features. Then, based on the consideration of the topology relationship between adjacent and cross-frame, graph convolutional network is introduced to infer the likelihood of linkage between frame nodes. Experiments show that the method demonstrates excellent scalability in addition to being an effective response to person clustering in case of changes, and does not need the number of clusters as a prior.
This paper proposes an automatic data extraction algorithm for web pages based on noise reduction and visualization blocks' construction. In this algorithm, we first build an MD5 trigeminal tree of the web page...
详细信息
With the growing popularity of API-driven multiservice application (mashup) development, the burgeoning web APIs have left developers drowning in the sea of web API selections. Matching developers with the most approp...
With the growing popularity of API-driven multiservice application (mashup) development, the burgeoning web APIs have left developers drowning in the sea of web API selections. Matching developers with the most appropriate APIs is the key to improving user satisfaction and promoting more popular web applications. As a result, more and more researchers pay attention to web API recommender systems based on collaborative filtering. However, employing collaborative filtering to recommend APIs is challenging due to the severe sparsity of mashup and API interactions. To address this problem, we propose a probabilistic generative model, called the Binary-API Topic model (BAT), to parameterize mashups and APIs. Technically, BAT is equipped with a mechanism to extract binary-APIs and predict unknown pairwise interactions. To improve generality and capture more relevance from a limited number of interactions, we learn binary-API topics by directly modeling the generation of API co-occurrence patterns across the repository (all mashup collections from ***). The main advantage of BAT is that it preserves API co-occurrence patterns in model learning and exploits the rich global relevance. Finally, through extensive experiments, we demonstrate that BAT can achieve the highest performance on the sparse real-world data set.
The data structure is becoming more and more complex, and the scale of the data set is getting larger and larger. The strong limitations and instability in the high-dimensional data environment is showed in traditiona...
详细信息
The mining of software community structure is of great significance in identifying software design pattern, software maintenance, software security and optimizing software structure. To improve the accuracy of descrip...
详细信息
Given that analysis on the vulnerability of functions is helpful to the detection and improvement of software security, this paper aims to propose an efficient methods to identify the vulnerable nodes (ITVN) in differ...
详细信息
With the rapid development of artificial intelligence, deep learning models have been applied in the field of society (e.g., video or image representation). However, due to the presence of adversarial examples, these ...
With the rapid development of artificial intelligence, deep learning models have been applied in the field of society (e.g., video or image representation). However, due to the presence of adversarial examples, these models exhibit obvious fragility, which has become a major challenge restricting society development. Therefore, studying the generation process and achieving high transferability of adversarial examples are of utmost importance. In this paper, we propose a transferable targeted adversarial attack method called Multi-source Perturbation Generation and integration (MPGI) to address the vulnerability and uncertainty of deep learning models. Specifically, MPGI consists of three critical designs to achieve targeted transferability of adversarial examples. Firstly, we propose a Collaborative Feature Fusion (CFF) component, which reduces the impact of original example feature on model classification by considering collaboration in feature fusion. Subsequently, we propose a Multi-scale Perturbation Dynamic Fusion (MPDF) module to fuse perturbations from different scales for enriching perturbation diversity. Finally, we innovatively investigate a novel Logit Margin with Penalty (LMP) loss to further enhance the misleading ability of the examples. The LMP, as a pluggable part, offers the potential to be leveraged by different approaches for boosting performance. In summary, MPGI can effectively achieve targeted attacks, expose the shortcomings of existing models, and promote the development of artificial intelligence in terms of security. Extensive experiments on ImageNet-Compatible and CIFAR-10 datasets demonstrate the superiority of the proposed method. For instance, the attack success rate increases by 17.6% and 17.0% compared to state-of-the-art method when transferred from DN-121 to Inc-v3 and MB-v2 models.
Depth estimation is an essential task for understanding the geometry of 3D scenes. Compared with multi-view-based methods, monocular depth estimation is more challenging for the requirement of integrating not only glo...
详细信息
暂无评论