The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple tasks. These networks are typically trained independently for each task by varying the output layer(s) and training objective. In this work we present a new model for...
Convolutional neural networks (CNNs) have been the mainstream in many computer vision tasks, such as image classification, object detection, face recognition and so on. We survey the state-of-the-art results on Pascal VOC 2012 semantic segmentation challenge which has made great progresses in 2015. We investigate the effectiveness of the new layers, structures and strategies behind these results proposed...
This paper presents our semantic mediation architecture for homogeneously retrieving data from big data. The architecture is split into three layers to find relevant answers of this data. In the proposed ontology-based approach, we use our domain ontology on alimentation risks field as well as a global schema of mediator and we apply the summarization process based on ontology for describes part of...
In this paper, we propose a convolutional framework for short texts expansion and classification. Particularly, by using additive composition over word embeddings from context with variable window width, the representations of multi-scale semantic units are computed first. Empirically, the semantically related words are usually close to each other in embedding spaces. Thus, the restricted nearest...
In classifying images, scenes or objects, the most popular approach is based on the features extraction-coding-pooling framework allowing to generate discriminative and robust image representations from densely extracted local patches, mainly some SIFT/HOG ones. The majority of the latest research is focused on how to improve successfully these coding and pooling parts. In this work, we show that...
Scene recognition is an important problem in the field of computer vision, because it helps to narrow the gap between the computer and the human beings on scene understanding. Semantic modeling is a popular technique used to fill the semantic gap in scene recognition. However, most of the semantic modeling approaches learn shallow, one-layer representations for scene recognition, while ignoring the...
Scene understanding is a critical issue in the advances of intelligent space. Given a 3D point cloud captured for a static scene by laser scanning, we propose a structure-based scene representation and object recognition method. Our method consists of three steps: (1) the scene is segmented and all of the segmented objects in scanned scene are described respectively by features, including size, location,...
Software Engineering is concerned with systematic delivery of products and services which meet the requirement posed by system stakeholders. One better way to make requirements from stakeholders (problem domain) understandable to developers (solution domain) is to transform such requirements into features. These features can be seen to interact with each other to perform system functionality according...
Media mining, the extraction of meaningful knowledge from multimedia content has become a major application and poses significant computational challenges in today's platforms. Media mining applications contain many sophisticated algorithms that include data-intensive analysis, classification, and learning. This paper explores the use of Graphics Processing Units (GPU) in media mining. We are particularly...
We present a cognitive architecture that heavily utilizes metareasoning for self adaptation. The architecture is derived in part from neuroscience data and theories about the operation of the human vision system. We also discuss how this architecture is applied in the POIROT system, which learns web services workflow from “observing” a small number of expert examples.
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.