The four-volume set LNCS 7333-7336 constitutes the refereed proceedings of the 12th International Conference on Computational science and Its Applications, ICCSA 2012, held in Salvador de Bahia, Brazil, in June 2012.;...
详细信息
ISBN:
(数字)9783642310751
ISBN:
(纸本)9783642310744
The four-volume set LNCS 7333-7336 constitutes the refereed proceedings of the 12th International Conference on Computational science and Its Applications, ICCSA 2012, held in Salvador de Bahia, Brazil, in June 2012.;The four volumes contain papers presented in the following workshops: 7333 - advances in high performance algorithms and applications (AHPAA); bioinspired computing and applications (BIOCA); computational geometry and applicatons (CGA); chemistry and materials sciences and technologies (CMST); cities, technologies and planning (CTP); 7334 - econometrics and multidimensional evaluation in the urban environment (EMEUE); geographical analysis, urban modeling, spatial statistics (Geo-An-Mod); 7335 - optimization techniques and applications (OTA); mobile communications (MC); mobile-computing, sensind and actuation for cyber physical systems (MSA4CPS); remote sensing (RS); 7336 - software engineering processes and applications (SEPA); software quality (SQ); security and privacy in computational sciences (SPCS); soft computing and data engineering (SCDE).;The topics of the fully refereed papers are structured according to the four major conference themes: 7333 - computational methods, algorithms and scientific application; 7334 - geometric modelling, graphics and visualization; 7335 - information systems and technologies; 7336 - high performance computing and networks.
This book explores the development of several new learning algorithms that utilize recent optimization techniques and meta-heuristics. It addresses well-known models such as particle swarm optimization, genetic algori...
详细信息
ISBN:
(数字)9789819638499
ISBN:
(纸本)9789819638482;9789819638512
This book explores the development of several new learning algorithms that utilize recent optimization techniques and meta-heuristics. It addresses well-known models such as particle swarm optimization, genetic algorithm, ant colony optimization, evolutionary strategy, population-based incremental learning, and grey wolf optimizer for training neural networks. Additionally, the book examines the challenges associated with these processes in detail. This volume will serve as a valuable reference for individuals in both academia and industry.
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.
Payment Channel Networks (PCNs), pivotal for blockchain scalability, facilitate multiple off-chain payments between any two users. They utilize scripts to define and execute payment conditions in various blockchains, ...
详细信息
Payment Channel Networks (PCNs), pivotal for blockchain scalability, facilitate multiple off-chain payments between any two users. They utilize scripts to define and execute payment conditions in various blockchains, but this poses privacy, efficiency, and compatibility challenges. To overcome these, scriptless cleverly embeds payment conditions into digital signatures instead of complex scripts. Cryptography effectively safeguards the construction and publication of transactions in script-based and scriptless PCNs. Although several surveys analyze PCN protocols, only a few discuss their underlying scripting languages and even none explore the cryptography involved. This survey is the first to comprehensively overview cryptography in PCNs from scripting perspectives, filling the existing knowledge void. Our analysis offers a complete picture of script-based and scriptless protocols and their coexistence. We then explore advanced cryptographic primitives in both categories, systematically studying these for the first time, and demonstrate their instantiations in atomic swaps. Finally, we research vast related surveys and provide a future-oriented outlook.
Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by th...
详细信息
Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus spotting pipeline of human beings and impressive performances of Pre-trained Language Models (PLMs) on visual tasks, we ask: 1) “Can machines spot texts without precise detection just like human beings?”, and if yes, 2)“Is text block another alternative for scene text spotting other than word or character?” To this end, our proposed scene text spotter leverages advanced PLMs to enhance performance without fine-grained detection. Specifically, we first use a simple detector for block-level text detection to obtain rough positional information. Then, we finetune a PLM using a large-scale OCR dataset to achieve accurate recognition. Benefiting from the comprehensive language knowledge gained during the pre-training phase, the PLM-based recognition module effectively handles complex scenarios, including multi-line, reversed, occluded, and incomplete-detection texts. Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks. Additionally, we attempt to spot texts directly from an entire scene image to demonstrate the potential of PLMs, even Large Language Models (LLMs).
The four-volume set LNCS 7333-7336 constitutes the refereed proceedings of the 12th International Conference on Computational science and Its Applications, ICCSA 2012, held in Salvador de Bahia, Brazil, in June 2012. ...
详细信息
ISBN:
(数字)9783642311284
ISBN:
(纸本)9783642311277
The four-volume set LNCS 7333-7336 constitutes the refereed proceedings of the 12th International Conference on Computational science and Its Applications, ICCSA 2012, held in Salvador de Bahia, Brazil, in June 2012. The four volumes contain papers presented in the following workshops: 7333 - advances in high performance algorithms and applications (AHPAA); bioinspired computing and applications (BIOCA); computational geometry and applicatons (CGA); chemistry and materials sciences and technologies (CMST); cities, technologies and planning (CTP); 7334 - econometrics and multidimensional evaluation in the urban environment (EMEUE); geographical analysis, urban modeling, spatial statistics (Geo-An-Mod); 7335 - optimization techniques and applications (OTA); mobile communications (MC); mobile-computing, sensind and actuation for cyber physical systems (MSA4CPS); remote sensing (RS); 7336 - software engineering processes and applications (SEPA); software quality (SQ); security and privacy in computational sciences (SPCS); soft computing and data engineering (SCDE). The topics of the fully refereed papers are structured according to the four major conference themes: 7333 - computational methods, algorithms and scientific application; 7334 - geometric modelling, graphics and visualization; 7335 - information systems and technologies; 7336 - high performance computing and networks.
暂无评论