We are delighted to welcome you to the proceedings of the 1st International Conference on Semantic and Digital Media Technologies held in Athens. SAMT 2006 aims to narrowthe large disparity between the low-level descr...
详细信息
ISBN:
(数字)9783540493372
ISBN:
(纸本)9783540493358
We are delighted to welcome you to the proceedings of the 1st International Conference on Semantic and Digital Media Technologies held in Athens. SAMT 2006 aims to narrowthe large disparity between the low-level descr- tors that can be computed automatically from multimedia content and the ri- ness and subjectivity of semantics in user queries and human interpretations of audiovisual media — The Semantic Gap. SAMT started out as two workshops, EWIMT 2004 and EWIMT 2005, that quickly achieved success in attracting high-quality papers from across Europe and beyond. This year EWIMT turned into the full-?edged conference SAMT, bringing together forums, projects, - stitutions and individuals investigating the integration of knowledge, semantics and low-level multimedia processing, and linking them with industrial engineers who exploit the underlying emerging technology. In total, 68 papers were submitted to the SAMT 2006 conference and each was reviewed by at least two independent reviewers. We are grateful to the membersoftheTechnicalProgramCommitteewhocompletedthesereviewsand allowed us to put together a very strong technical program of 17 papers. The selection process was very competitive with only 25% of papers being selected for oral presentation. The program also included two invited keynote talks from Alan Smeaton and Guus Schreiber, and we are very grateful to them for their insightful presentations.
The Cross-lingual Dependency Parsing (XDP) task poses a significant challenge due to the differences in dependency structures between training and testing languages, known as the out-of-distribution (OOD) problem. Our...
详细信息
The Cross-lingual Dependency Parsing (XDP) task poses a significant challenge due to the differences in dependency structures between training and testing languages, known as the out-of-distribution (OOD) problem. Our research delved into this issue in the XDP dataset by selecting 43 languages from 22 language families. We found that the primary factor of the OOD problem is the unbalanced length distribution among languages. To address the impact of the OOD problem, we propose deep stable learning for Cross-lingual Dependency Parsing (SL-XDP), which utilizes deep stable learning with a feature fusion module. In detail, we implemented five feature fusion operations for generating comprehensive representations with dependency relations and the deep stable learning algorithm to decorrelate dependency structures with sequence length. Our experiments on Universal Dependencies have demonstrated that SL-XDP can lessen the impact of the OOD problem and improve the model generalization among 21 languages, with a maximum improvement of 18%.
Knowledge graphs have proven highly effective for learning representations of entities and relations, with hyper-relational knowledge graphs (HKGs) gaining increased attention due to their enhanced representation capa...
详细信息
Knowledge graphs have proven highly effective for learning representations of entities and relations, with hyper-relational knowledge graphs (HKGs) gaining increased attention due to their enhanced representation capabilities. Each fact in an HKG consists of a main triple supplemented by attribute-value qualifiers that provide additional contextual information. Due to the complexity of hyper-relations, HKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, often mixed together. However, previous work mainly embeds HKGs into Euclidean space, limiting their ability to capture these complex geometric structures simultaneously. To address this challenge, we propose a novel model called Geometry Aware Hyper-relational Embedding (GAHE). Specifically, GAHE adopts a multi-curvature geometry-aware approach by modeling HKGs in Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature) in a unified framework. In this way, it can integrate space-invariant and space-specific features to accurately capture the diverse structures in HKGs. In addition, GAHE introduces a module termed hyper-relational subspace learning, which allocates multiple sub-relations for each hyper-relation. It enables the exploitation of abundant latent semantic interactions and facilitates the exploration of fine-grained semantics between attribute-value pairs and hyper-relations across multiple subspaces. Furthermore, we provide theoretical guarantees that GAHE is fully expressive and capable of modeling a wide range of semantic patterns for hyper-relations. Empirical evaluations demonstrate that GAHE achieves state-of-the-art results on both hyper-relational and binary-relational benchmarks.
Visual informatics is a field of interest not just among the informationtechnology and computer science community, but also other related fields such as engineering, me- cal and health informatics and education start...
详细信息
ISBN:
(数字)9783642050367
ISBN:
(纸本)9783642050350
Visual informatics is a field of interest not just among the informationtechnology and computer science community, but also other related fields such as engineering, me- cal and health informatics and education starting in the early 1990s. Recently, the field is gaining more attention from researchers and industry. It has become a mul- disciplinary and trans-disciplinary field related to research areas such as computer vision, visualization, information visualization, real-time image processing, medical image processing, image information retrieval, virtual reality, augmented reality, - pressive visual mathematics, 3D graphics, multimedia-fusion, visual data mining, visual ontology, as well as services and visual culture. Various efforts has been - vested in different research, but operationally, many of these systems are not pro- nent in the mass market and thus knowledge and research on these phenomena within the mentioned areas need to be shared and disseminated. It is for this reason that the Visual Informatics Research Group from Universiti - bangsaan Malaysia (UKM) decided to spearhead this initiative to bring together experts in this very diversified but important research area so that more concerted efforts can be undertaken not just within the visual informatics community in Malaysia but from other parts of the world, namely, Asia, Europe, Oceania, and USA. This first International Visual Informatics Conference (IVIC 2009) was conducted collaboratively, by the visual informatics research community from the various public and private institutions of higher learning in Malaysia, and hosted by UKM.
The rise of the digital economy and e-commerce has fostered a movement towards efficient low-resource medical informationprocessing, a trend that holds great importance in the healthcare sector. Diabetes, being a wid...
详细信息
The rise of the digital economy and e-commerce has fostered a movement towards efficient low-resource medical informationprocessing, a trend that holds great importance in the healthcare sector. Diabetes, being a widespread chronic condition, has witnessed the introduction of glucometers, which offer patients a convenient method of monitoring their blood sugar levels. However, it is worth noting that a considerable proportion of online comments may be subject to emotional bias or contain inaccurate information. Furthermore, the performance of glucometers can be influenced by several attributes, including price, accuracy and portability, thereby potentially complicating the decision-making process for consumers. Semantic analysis can be employed to acquire valuable information, aiding consumers in reasonably choosing the suitable glucometer. This paper utilizes the benefits of granular computing, an emerging computing paradigm, to effectively handle incomplete and uncertain medical information. It employs generalized fuzzy sets, rough sets and three-way decisions (TWD) techniques to boost the accuracy and reliability of medical information fusion. Subsequently, the MABAC (Multi-Attribute Border Approximation Area Comparison) method is utilized to evaluate the reviews of every glucometer, calculate their aggregated scores, and rank and compare them. Ultimately, in light of consumers’ needs and trade-offs, the glucometer with the highest score can be selected. The proposed approach comprehensively considers the weight and priority of multiple attributes, reduces information overload and mitigates selection difficulties, thereby enhancing the accuracy and reliability of low-resource medical informationprocessing.
Collaborative Filtering (CF) is a pivotal research area in recommender systems that capitalizes on collaborative similarities between users and items to provide personalized recommendations. With the remarkable achiev...
详细信息
Collaborative Filtering (CF) is a pivotal research area in recommender systems that capitalizes on collaborative similarities between users and items to provide personalized recommendations. With the remarkable achievements of node embedding-based Graph Neural Networks (GNNs), we explore the upper bounds of expressiveness inherent to embedding-based methodologies, and tackle the challenges by reframing the CF task as a graph-signal processing problem. To this end, we propose PolyCF, a flexible graph signal filter that leverages polynomial graph filters to process interaction signals. PolyCF exhibits the capability to capture spectral features across multiple eigenspaces through a series of Generalized Gram filters, and is able to approximate the optimal polynomial response function for recovering missing interactions. A graph optimization objective and a pair-wise ranking objective are jointly used to optimize the parameters of the convolution kernel. Experiments on three widely adopted datasets demonstrate the superiority of PolyCF over the state-of-the-art CF methods.
暂无评论