Semantic segmentation is an essential part of deep learning. In recent years, with the development remote sensing big data, semantic has been increasingly used in sensing. Deep convolutional neural networks (DCNNs) face challenge feature fusion: very-high-resolution image multisource data fusion can increase network's learnable information, which conducive to correctly classifying target object...

Abstract Are we made up entirely and without residue of the data that defines us, or is there a disjunction between our shadows embodied selves? How do come to recognize ourselves, selves, in pronouns interpellate us online, what it exactly recognize? What does mean occupy semantic positional space pronoun ‘you’? And continuity discontinuity systems surveillance aggregation address don’t? The m...

Hyperspectral Imaging (HSI) provides detailed spectral information and has been utilised in many real-world applications. This work introduces an HSI dataset of building facades a light industry environment with the aim classifying different materials scene. The is called Light Industrial Building (LIB-HSI) dataset. consists nine categories 44 classes. In this study, we investigated deep learni...

The concept of IoT (Internet Things) assumes a continuous increase in the number devices, which raises problem classifying them for different purposes. Based on their semantic characteristics, meaning, functionality or domain usage, system classes have been identified so far. This research purpose is to identify devices based traffic flow characteristics such as coefficient variation received a...

A long-standing linguistic hypothesis asserts that the meanings of words are related to the contexts in which they appear (Miller and Charles 1991). This paper explores this hypothesis by showing that co-occurrences of discourse markers reflect the meanings of the discourse markers themselves. An experiment in classifying discourse markers by their semantic class, e.g. temporal or causal, was c...

This paper explores the incorporation of lexico-semantic heuristics into a deterministic Coreference Resolution (CR) system for classifying named entities at document-level. The highest precise sieves of a CR tool are enriched with both a set of heuristics for merging named entities labeled with different classes and also with some constraints that avoid the incorrect merging of similar mention...

There is no standard set of semantic relations for classifying noun-noun compounds. This paper describes the development of a new annotation scheme which fulfils a number of desirable criteria. A rigorous dual-annotator experiment indicates that reasonably good agreement can be achieved but that the task remains a very difficult one. Analysis of the annotators' disagreements suggests which cate...

Named Entity Recognition and Classification (NERC) is a well-studied NLP task typically focused on coarse-grained named entity (NE) classes. NERC for more fine-grained semantic NE classes has not been systematically studied. This paper quantifies the difficulty of fine-grained NERC (FG-NERC) when performed at large scale on the people domain. We apply unsupervised acquisition methods to constru...

This paper strives for demonstrating “metamodels in action” which means showing concrete applications of this concept. Based on a literature survey we develop a taxonomy that helps classifying existing application scenarios concerning the dimensions of domain, design, and integration and briefly describe some of the existing work we came across. Furthermore, we provide an insight into the area ...

This paper presents a novel framework for training models to recognise simple spatial-motion events, such as those described by the verbs pick up, put down, push, pull, drop, tip, and tap and classifying novel observations into previously trained classes. Simple colourand motionbased segmentation and tracking techniques are used to produce a time series of feature vectors constructed from the 2...