Topic
Representation (systemics)
About: Representation (systemics) is a research topic. Over the lifetime, 33821 publications have been published within this topic receiving 475461 citations.
Papers published on a yearly basis
Papers
More filters
01 Jan 2002
TL;DR: In this paper, the authors describe a means for linking a model and object representa- tions of geographical space based on a series of mappings, where locations in a continuous eeld are mapped to discrete objects.
Abstract: This paper describes a means for linking eeld and object representa- tions of geographical space. The approach is based on a series of mappings, where locations in a continuous eeld are mapped to discrete objects. An object in this context is a modeler's conceptualization, as in a viewshed, highway corridor or biological reserve. An object can be represented as a point, line, polygon, network, or other complex spatial type. The relationship between locations in a eeld and spatial objects may take the form of one-to-one, one-to-many, many-to-one, or many-to-many. We present a typology of object eelds and discuss issues in their construction, storage, and analysis. Example applications are presented and directions for further research are oVered.
166 citations
01 Aug 2013
TL;DR: A novel disambiguation model, based on neural networks that learns distributed representation of entity to measure similarity without man-made features, achieves a good performance on two datasets without any manually designed features.
Abstract: In this paper we present a novel disambiguation model, based on neural networks. Most existing studies focus on designing effective man-made features and complicated similarity measures to obtain better disambiguation performance. Instead, our method learns distributed representation of entity to measure similarity without man-made features. Entity representation consists of context document representation and category representation. Document representation of an entity is learned based on deep neural network (DNN), and is directly optimized for a given similarity measure. Convolutional neural network (CNN) is employed to obtain category representation, and shares deep layers with DNN. Both models are trained jointly using massive documents collected from Baike http://baike.baidu.com/. Experiment results show that our method achieves a good performance on two datasets without any manually designed features.
166 citations
14 Jun 2020
TL;DR: A novel self-supervised method, referred to as video Playback Rate Perception (PRP), to learn spatio-temporal representation in a simple-yet-effective way and outperforms state-of-the-art self- supervised models with significant margins.
Abstract: In self-supervised spatio-temporal representation learning, the temporal resolution and long-short term characteristics are not yet fully explored, which limits representation capabilities of learned models. In this paper, we propose a novel self-supervised method, referred to as video Playback Rate Perception (PRP), to learn spatio-temporal representation in a simple-yet-effective way. PRP roots in a dilated sampling strategy, which produces self-supervision signals about video playback rates for representation model learning. PRP is implemented with a feature encoder, a classification module, and a reconstructing decoder, to achieve spatio-temporal semantic retention in a collaborative discrimination-generation manner. The discriminative perception model follows a feature encoder to prefer perceiving low temporal resolution and long-term representation by classifying fast-forward rates. The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism. PRP is applied on typical video target tasks including action recognition and video retrieval. Experiments show that PRP outperforms state-of-the-art self-supervised models with significant margins. Code is available at github.com/yuanyao366/PRP.
165 citations
TL;DR: The impact of the ontic vs. epistemic sets distinction in statistics is examined to show its importance because there is a risk of misusing basic notions and tools, such as conditioning, distance between sets, variance, regression, etc. when data are set-valued.
165 citations
10 Sep 2010
TL;DR: This paper proposes to use objects as attributes of scenes for scene classification, and shows that this object-level image representation can be used effectively for high-level visual tasks such as scene classification.
Abstract: Robust low-level image features have proven to be effective representations for a variety of high-level visual recognition tasks, such as object recognition and scene classification. But as the visual recognition tasks become more challenging, the semantic gap between low-level feature representation and the meaning of the scenes increases. In this paper, we propose to use objects as attributes of scenes for scene classification. We represent images by collecting their responses to a large number of object detectors, or "object filters". Such representation carries high-level semantic information rather than low-level image feature information, making it more suitable for high-level visual recognition tasks. Using very simple, off-the-shelf classifiers such as SVM, we show that this object-level image representation can be used effectively for high-level visual tasks such as scene classification. Our results are superior to reported state-of-the-art performance on a number of standard datasets.
164 citations