Zhiyong Feng

Zhiyong Feng
Tianjin University | tju · School of Computer Software

PhD

About

348
Publications
36,646
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,570
Citations
Citations since 2016
179 Research Items
2178 Citations
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
Additional affiliations
January 2016 - present
Tianjin University
Position
  • Professor (Full)
January 1999 - January 2016
Tianjin University
Position
  • Professor

Publications

Publications (348)
Preprint
Relation classification is to recognize semantic relation between two given entities mentioned in the given text in Knowledge Graph. Existing models have performed well on the inverse relation classification with large-scale datasets, but their performance drops significantly for few-shot learning. In this paper, we propose a novel method, function...
Chapter
Multilingual pre-trained language models (PLMs) facilitate zero-shot cross-lingual transfer from rich-resource languages to low-resource languages in extractive question answering (QA) tasks. However, during fine-tuning on the QA task, the syntactic information of languages in multilingual PLMs is not always preserved or even is forgotten, which ma...
Conference Paper
The relation classification is to identify semantic relations between two entities in a given text. While existing models perform well for classifying inverse relations with large datasets, their performance is significantly reduced for few-shot learning. In this paper, we propose a function words adaptively enhanced attention framework (FAEA) for...
Preprint
Full-text available
The relation classification is to identify semantic relations between two entities in a given text. While existing models perform well for classifying inverse relations with large datasets, their performance is significantly reduced for few-shot learning. In this paper, we propose a function words adaptively enhanced attention framework (FAEA) for...
Preprint
Full-text available
Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make answer spans predicted by zero-shot transfer violate syntactic constraints of the target language. In this paper, w...
Chapter
Cross-modal retrieval essentially extracts the shared semantics of an object between two different modalities. However, “modality gap” may significantly limit the performance when analyzing from each modality sample. In this paper, to overcome the characteristics from heterogeneous data, we propose a novel mutual information-based disentanglement f...
Article
Discovering communities is an essential step in the analysis of complex systems, and it has two purposes: to identify functional modules and to interpret semantics. However, most of the existing community detection methods only focused on identify communities, while learning the semantics interpretation of communities has not been fully studied. In...
Article
For the merits of high-order statistics and Riemannian geometry, covariance matrix has become a generic feature representation for action recognition. An independent action can be represented by an empirical statistics over all of its pose samples. Two major problems of covariance include the following: (1) it is prone to be singular so that action...
Chapter
Dependency-based models for the named entity recognition (NER) task have shown promising results by capturing long-distance relationships between words in a sentence. However, while existing models focus on the syntactic dependency between entities, we are unaware of any work that considers semantic dependency. In this work, we study the usefulness...
Chapter
Automatic text generation is widely used in dialogue systems, machine translation and other fields. Sequence Generative Adversarial Network (SeqGAN) has achieved good performance in text generation tasks. Due to the discriminator can only evaluate the finished text, and cannot provide other valid information to the generator. When evaluating a sing...
Chapter
Zero-Shot Action Recognition (ZSAR) aims to transfer knowledge from a source domain to a target domain so that the unlabelled action can be inferred and recognized. However, previous methods often fail to highlight information about the salient factors of the video sequence. In the process of cross-modal search, information redundancy will weaken t...
Article
Network embedding which is to learn a low dimensional representation of nodes in a network has been used in many network analysis tasks. Recently some Generative Adversarial Networks (GAN) based network embedding methods have been proposed. These methods typically use GAN to force the network embedding results to follow a priori distribution (e.g....
Article
Directed and undirected probabilistic graphical models have been successfully used in community detection in recent years, but existing graphical model based methods usually only use one type of probabilistic graphical model to discover communities. However, directed and undirected graphical models have their own advantages for characterizing diffe...
Article
Web services (or Web APIs) on the Internet tends to encounter various unexpected runtime failures because of their dynamicity and distribution. Self‐adaptation technologies for the service‐based business process can effectively repair runtime failures and improve its success rate. However, the same failures may occur on subsequent invocations becau...
Article
Full-text available
Ontology-mediated querying (OMQ) provides a paradigm for query answering according to which users not only query records at the database but also query implicit information inferred from ontology. A key challenge in OMQ is that the implicit information may be infinite, which cannot be stored at the database and queried by off -the -shelf query engi...
Article
Despite the promising progress made in recent years, individual identification from biological motion remains a challenging task due to the drastic changes in human poses produced by various covariate factors. A variety of algorithms have been proposed to solve this challenging problem by extracting the invariant features of individuals. There exis...
Article
Despite the rapid increase of research on individual identification in recent years, most of them focused on extracting the invariant visual cues of individuals. However, few efforts have been devoted to exploring the inherent feature caused by physiological differences. The main challenge in this task arises from two aspects: (i) the individual in...
Article
Most Zero-Shot Action Recognition (ZSAR) methods establish visual-semantic joint embedding space, which is based on commonly used visual features and semantic embeddings, to learn the correlation between actions. Nevertheless, extracting visual features without structural guidance would lead to sparse video features, which reflect the correlation o...
Chapter
With the vigorous development of the platform-based service ecosystem represented by e-commerce, service recommendation is used as a personalized matching method. There exist some service recommendation strategies that mainly focus on high popularity services and ignore non-popular ones. This will not only lead to oligopoly, but also be detrimental...
Chapter
Trans-boundary and integration are important characteristics of the development of modern service industry. With the development of Internet technology, trans-boundary cooperation between domains constantly emerges, which drives the development of service ecosystem. Currently, there is a lack of an appropriate model for analyzing the impact of tran...
Chapter
Detecting users’ significant intentions (e.g., new features wanted) timely and precisely is crucial for developers to update and maintain their apps in the competitive mobile app market. Sentiment and preference mining from crowd reviews provide an opportunity to proactively collect app users’ intentions, e.g., bug fixing and feature refinement. Ho...
Article
In most supervised action recognition methods, sufficient labeled training instances are needed for each class, the learned model can only recognize the samples belonging to classes covered by the training data, and lacks the ability to deal with previously unseen classes. In this paper, we tackle the above challenges by proposing a novel Video Dis...
Preprint
With the development of cloud computing, service computing, IoT(Internet of Things) and mobile Internet, the diversity and sociality of services are increasingly apparent. To meet the customized user demands, Service Ecosystem is emerging as a complex social-technology system, which is formed with various IT services through cross-border integratio...
Article
With the aging of the population and the development of modern service industries, the health service ecosystem (HSE) is beginning to emerge. As a new form of healthcare industry in the Internet era, HSE has its inherent “social cyber” complexity: the source of healthcare service is social, and such sociality aggravates the diversity, uncertainty,...
Conference Paper
Community detection, aiming at partitioning a network into multiple substructures, is practically importance. Graph convolutional network (GCN), a new deep-learning technique, has recently been developed for community detection. Markov Random Fields (MRF) has been combined with GCN in the MRFasGCN method to improve accuracy. However, the existing G...
Article
Android utilizes a security mechanism that requires apps to request permission for accessing sensitive user data, e.g., contacts and SMSs, or certain system features, e.g., camera and Internet access. However, Android apps tend to be overprivileged, i.e., they often request more permissions than necessary. This raises the security problem of overpr...
Article
Complex networks are widely used in the research of social and biological fields. Analyzing real community structure in networks is the key to the study of complex networks. Modularity optimization is one of the most popular techniques in community detection. However, due to its greedy characteristic, it leads to a large number of incorrect partiti...
Article
Full-text available
An ontology language for ontology mediated query answering (OMQA-language) is universal for a family of OMQA-languages if it is the most expressive one among this family. In this paper, we focus on three families of tractable OMQA-languages, including first-order rewritable languages and languages whose data complexity of the query answering is in...
Article
Full-text available
More users suffering from depression turn to online forums to express their problems and seek help. In such forums, there is often a large volume of posts with sensitive content, indicating that the user has a risk of suicide and self-harm. Early detection of depression using appropriate deep learning models and social media data can prevent potent...
Article
In this paper, we introduce cross-covariance to form Symmetric Positive Definite(SPD) matrix-based representations for 3D action recognition. The cross-covariance is generated by the correlational statistics between the time-shifted poses, which brings more informative features and time-order structure to improve the discriminative power on actions...
Article
Individual recognition from locomotion is a challenging task owing to large intra-class and small inter-class variations. In this article, we present a novel metric learning method for individual recognition from skeleton sequences. Firstly, we propose to model articulated body on Riemannian manifold to describe the essence of human motion, which c...
Preprint
Full-text available
Android utilizes a security mechanism that requires apps to request permission for accessing sensitive user data, e.g., contacts and SMSs, or certain system features, e.g., camera and Internet access. However, Android apps tend to be overprivileged, i.e., they often request more permissions than necessary. This raises the security problem of overpr...
Article
Although Deep Convolutional Neural Networks (DCNNs) facilitate the evolution of 3D human pose estimation, ambiguity remains the most challenging problem in such tasks. Inspired by the Human Perception Mechanism (HPM), we propose an image-to-pose coding method to fill the gap between image cues and 3D poses, thereby alleviating the ambiguity of 3D h...
Preprint
BACKGROUND The process of developing new drugs is very tortuous. Bringing new drugs to the market requires billions of dollars in investment, which takes an average of about 13-15 years. In order to overcome these difficulties, more and more companies and pharmaceutical companies have begun to adopt the strategy of “repositioning drugs” instead of...
Preprint
Full-text available
An ontology language for ontology mediated query answering (OMQA-language) is universal for a family of OMQA-languages if it is the most expressive one among this family. In this paper, we focus on three families of tractable OMQA-languages, including first-order rewritable languages and languages whose data complexity of the query answering is in...
Conference Paper
Full-text available
In this paper, we propose a holistic solution to address several important and challenging issues in storage data management in light of emerging NVDIMM-based architecture: namely, new performance modeling, NVDIMM-based migration, and architectural support for NVDIMMs on migration optimization. In particular, a novel NVDIMM-based heterogeneous stor...
Chapter
All neural networks are not always effective in processing imbalanced datasets when dealing with text classification due to most of them designed under a balanced assumption. In this paper, we present a novel framework named BSIL to improve the capability of neural networks in imbalanced text classification built on brain storm optimization (BSO)....
Chapter
Deep learning (DL) systems are increasingly used in security-related fields, where the accuracy and predictability of DL systems are critical. However the DL models are difficult to test and existing DL testing relies heavily on manually labeled data and often fails to expose erroneous behavior for corner inputs. In this paper, we propose Different...
Chapter
Vehicular Ad Hoc Network (VANET) is a special application of traditional Mobile Ad Hoc Network (MANET) in traffic roads, which has attracted extensive attention due to its important role in intelligent traffic and road services. In order to ensure the safety of road traffic and protect the privacy of users, it is of vital importance to provide effe...
Conference Paper
In this paper, we present a neural network (InteractionNN) for sparse predictive analysis where hidden features of sparse data can be learned by multilevel feature interaction. To characterize multilevel interaction of features, InteractionNN consists of three modules, namely, nonlinear interaction pooling, layer-lossing, and embedding. Nonlinear i...
Conference Paper
Markov Random Field (MRF) has been successfully used in community detection recently. However, existing MRF methods only utilize the network topology while ignore the semantic attributes. A straightforward way to combine the two types of information is that, one can first use a topic clustering model (e.g. LDA) to derive group membership of nodes b...
Conference Paper
Full-text available
AI benchmarking becomes an increasingly important task. As suggested by many researchers, Intelligence Quotient (IQ) tests, which is widely regarded as one of the predominant benchmarks for measuring human intelligence, raises an interesting challenge for AI systems. For better solving IQ tests automatedly by machines, one needs to use, combine and...
Article
Full-text available
Trans-boundary has become not only a trend but also an important requirement and feature of Modern Service Industry. In Internet era, crossover service not only changes people's daily life, but also has a profound impact on the business model of traditional industry. However, because of the complexity and convergence of crossover service, it is dif...
Conference Paper
In this paper, we lead the first efforts towards intelligent RDF data management in SSDs. We propose to deeply fuse the RDF data in SSDs. In detail, the operations (e.g., data query) applied to RDF can be directly achieved in SSDs. To this end, we explore two RDF data organizations (e.g., triple-based) with the consideration of the internal structu...
Poster
Full-text available
Most covariance-based representations of actions are focused on the statistical features of poses by empirical averaging weighting. Note that these poses have a variety of saliency levels for different actions. Neglecting pose saliency could degrade the discriminative power of the covariance features, and further reduce the performance of action re...
Article
To pave the way for fast data access, multiple parallel components (e.g., multiple dies) in SSDs are crafted. Therefore, how to fully utilize the parallel resources has become a challenging issue. To address this issue, we first design an SSD model, which not only considers the structure of the parallel components in SSDs but also investigates the...
Chapter
In this paper, we present gSMat, a SPARQL query engine for RDF datasets. It employs join optimization and data sparsity. We bifurcate gSMat into three submodules e.g. Firstly, SM Storage (Sparse Matrix-based Storage) which lifts the storage efficiency, by storing valid edges, introduces a predicate-based hash index on the storage and generate a sta...