Réseau sémantique

Résumé

Un réseau sémantique est un graphe marqué destiné à la représentation des connaissances, qui représente des relations sémantiques entre concepts. Le graphe est orienté ou non orienté. Ses sommets représentent les concepts, et les liens entre les sommets (nœuds) représentent les relations sémantiques, reliant les champs lexicaux. Un réseau sémantique peut être instancié, par exemple,dans une base de données orientée graphes ou un schéma conceptuel. Les réseaux sémantiques normalisés sont exprimés sous forme de triplets RDF. La première utilisation connue, au IIIème siècle, est un commentaire du philosophe grec Porphyre sur les catégories d'Aristote. En psychologie, dans les années 1960, Quillian et Collins s'en sont d'abord servi pour modéliser l'usage des taxonomies dans la mémoire sémantique. Ces réseaux ont ensuite été employés par exemple pour gérer des thésaurus, pour modéliser la signification d'un texte, ou en robotique pour modéliser les états d'un système en vue d'élabore

Source officielle

https://fr.wikipedia.org/wiki/R%C3%A9seau_s%C3%A9mantique

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (59)

Publications associées

Chargement

Personnes associées (6)

Personnes associées

Chargement

Unités associées (5)

Unités associées

Chargement

Concepts associés (28)

Concepts associés

Chargement

Cours associés (7)

Cours associés

Chargement

Séances de cours associées (14)

Séances de cours associées

Chargement

Effectively managing a large collection of multimedia documents is a challenge, addressed by many disciplines from signal processing through database systems to artificial intelligence and interaction design. The problems to be solved have rarely been considered together. We propose a series of novel solutions for: the system architecture, the document content characterization, the retrieval methodology, and the user interaction schemes. We propose and describe a communicating components architecture using a new open and flexible protocol for messaging. Its foundation, the multimedia retrieval markup language (mrml) is specified with examples of the benefits of this approach. The general multimedia application domain is restricted mainly to image documents that carry semantic annotation like captions or meta-data. The integration of perceptual and semantic content descriptions into a single retrieval structure is the principal contribution of our work. The proposed method allows for improved effectiveness, augmented functionality and high flexibility for the extension to other media types like audio or video. The relationships among the two different representational characteristics can be exploited for more effective retrieval and other tasks like semi-automatic image annotation or illustration of semantic concepts. The final contribution is the study and implementation of user interaction metaphors that are intuitive and attempt to further bridge the gap between user's and system's notion of relevance. A rich set of information need formulation tools is proposed to users of varying skill and of varying requirements. Merging query specification with result visualization and browsing, using interactively explorable search spaces, offers a single access point to most retrieval tasks.

EPFL2003

Chargement

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval

Jie Luo, Mengshi Qi, Yiyu Wang, Yi Yang

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent the whole video, while ignoring visual pattern consistencies and intrinsic temporal relationships across different frames. Furthermore, the semantic correspondence between natural language queries and person-centric actions in videos has not been fully explored. To address these problems, we propose a novel binary representation learning framework, named Semanticsaware Spatial-temporal Binaries (S(2)Bin), which simultaneously considers spatial-temporal context and semantic relationships for cross-modal video retrieval. By exploiting the semantic relationships between two modalities, S(2)Bin can efficiently and effectively generate binary codes for both videos and texts. In addition, we adopt an iterative optimization scheme to learn deep encoding functions with attribute-guided stochastic training. We evaluate our model on three video datasets and the experimental results demonstrate that S(2)Bin outperforms the state-of-the-art methods in terms of various cross-modal video retrieval tasks.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Chargement

The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

Peter Clemens Schlicht

Enabling autonomous driving (AD) can be considered one of the biggest challenges in today?s technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception is usually performed by combining the semantic information captured by several sensors, i.e., lidar or camera. The semantic information from the respective sensor can be extracted by using convolutional neural networks (CNNs) for dense prediction. In the past, CNNs constantly showed stateof-the-art performance on several vision-related tasks, such as semantic segmentation of traffic scenes using nothing but the red-green-blue (RGB) images provided by a camera. Although CNNs obtain state-of-the-art performance on clean images, almost imperceptible changes to the input, referred to as adversarial perturbations, may lead to fatal deception. The goal of this article is to illuminate the vulnerability aspects of CNNs used for semantic segmentation with respect to adversarial attacks, and share insights into some of the existing known adversarial defense strategies. We aim to clarify the advantages and disadvantages associated with applying CNNs for environment perception in AD to serve as a motivation for future research in this field.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Chargement