Showing papers on "Representation (systemics) published in 2016"

Display screen or portion thereof with graphical user interface

Abstract: Newness and distinctiveness is claimed in the features of ornamentation as shown inside the broken line circle in the accompanying representation.

A survey on object detection in optical remote sensing images

Abstract: Object detection in optical remote sensing images, being a fundamental but challenging problem in the field of aerial and satellite image analysis, plays an important role for a wide range of applications and is receiving significant attention in recent years. While enormous methods exist, a deep review of the literature concerning generic object detection is still lacking. This paper aims to provide a review of the recent progress in this field. Different from several previously published surveys that focus on a specific object class such as building and road, we concentrate on more generic object categories including, but are not limited to, road, building, tree, vehicle, ship, airport, urban-area. Covering about 270 publications we survey (1) template matching-based object detection methods, (2) knowledge-based object detection methods, (3) object-based image analysis (OBIA)-based object detection methods, (4) machine learning-based object detection methods, and (5) five publicly available datasets and three standard evaluation metrics. We also discuss the challenges of current studies and propose two promising research directions, namely deep learning-based feature representation and weakly supervised learning-based geospatial object detection. It is our hope that this survey will be beneficial for the researchers to have better understanding of this research field.

Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking

Abstract: The accurate detection and classification of moving objects is a critical aspect of advanced driver assistance systems. We believe that by including the object classification from multiple sensor detections as a key component of the object's representation and the perception process, we can improve the perceived model of the environment. First, we define a composite object representation to include class information in the core object's description. Second, we propose a complete perception fusion architecture based on the evidential framework to solve the detection and tracking of moving objects problem by integrating the composite representation and uncertainty management. Finally, we integrate our fusion approach in a real-time application inside a vehicle demonstrator from the interactIVe IP European project, which includes three main sensors: radar, lidar, and camera. We test our fusion approach using real data from different driving scenarios and focusing on four objects of interest: pedestrian, bike, car, and truck.

Black Looks Race And Representation

Abstract: Thank you very much for reading black looks race and representation. As you may know, people have look numerous times for their favorite books like this black looks race and representation, but end up in harmful downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they are facing with some malicious bugs inside their computer. black looks race and representation is available in our digital library an online access to it is set as public so you can get it instantly. Our digital library saves in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Merely said, the black looks race and representation is universally compatible with any devices to read.

A Compositional Object-Based Approach to Learning Physical Dynamics

Abstract: We present the Neural Physics Engine (NPE), a framework for learning simulators of intuitive physics that naturally generalize across variable object count and different scene configurations. We propose a factorization of a physical scene into composable object-based representations and a neural network architecture whose compositional structure factorizes object dynamics into pairwise interactions. Like a symbolic physics engine, the NPE is endowed with generic notions of objects and their interactions; realized as a neural network, it can be trained via stochastic gradient descent to adapt to specific object properties and dynamics of different worlds. We evaluate the efficacy of our approach on simple rigid body dynamics in two-dimensional worlds. By comparing to less structured architectures, we show that the NPE's compositional representation of the structure in physical interactions improves its ability to predict movement, generalize across variable object count and different scene configurations, and infer latent properties of objects such as mass.

Concept Representation Reflects Multimodal Abstraction: A Framework for Embodied Semantics

Abstract: Recent research indicates that sensory and motor cortical areas play a significant role in the neural representation of concepts. However, little is known about the overall architecture of this representational system, including the role played by higher level areas that integrate different types of sensory and motor information. The present study addressed this issue by investigating the simultaneous contributions of multiple sensory-motor modalities to semantic word processing. With a multivariate fMRI design, we examined activation associated with 5 sensory-motor attributes--color, shape, visual motion, sound, and manipulation--for 900 words. Regions responsive to each attribute were identified using independent ratings of the attributes' relevance to the meaning of each word. The results indicate that these aspects of conceptual knowledge are encoded in multimodal and higher level unimodal areas involved in processing the corresponding types of information during perception and action, in agreement with embodied theories of semantics. They also reveal a hierarchical system of abstracted sensory-motor representations incorporating a major division between object interaction and object perception processes.

A Survey of Multi-View Representation Learning

Abstract: Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment and multi-view representation fusion. Consequently, we first review the representative methods and theories of multi-view representation learning based on the perspective of alignment, such as correlation-based alignment. Representative examples are canonical correlation analysis (CCA) and its several extensions. Then from the perspective of representation fusion we investigate the advancement of multi-view representation learning that ranges from generative methods including multi-modal topic learning, multi-view sparse coding, and multi-view latent space Markov networks, to neural network-based methods including multi-modal autoencoders, multi-view convolutional neural networks, and multi-modal recurrent neural networks. Further, we also investigate several important applications of multi-view representation learning. Overall, this survey aims to provide an insightful overview of theoretical foundation and state-of-the-art developments in the field of multi-view representation learning and to help researchers find the most appropriate tools for particular applications.

Neural Headline Generation on Abstract Meaning Representation

Abstract: Neural network-based encoder-decoder models are among recent attractive methodologies for tackling natural language generation tasks. This paper investigates the usefulness of structural syntactic and semantic information additionally incorporated in a baseline neural attention-based model. We encode results obtained from an abstract meaning representation (AMR) parser using a modified version of Tree-LSTM. Our proposed attention-based AMR encoder-decoder model improves headline generation benchmarks compared with the baseline neural attention-based model.

Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN

Abstract: Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential Deep Trajectory Descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDTD stream is introduced into a three-stream framework so as to identify actions from a video sequence. Consequently, this three-stream framework can simultaneously capture static spatial features, short-term motion and long-term motion in the video. Extensive experiments were conducted on three challenging datasets: KTH, HMDB51 and UCF101. Experimental results show that our method achieves state-of-the-art performance on the KTH and UCF101 datasets, and is comparable to the state-of-the-art methods on the HMDB51 dataset.

Generating object time series from data objects

Abstract: Systems and methods are presented for representing non-numerical data objects in an object time series. An object time series of can be created by establishing one or more associations, each association including a mapping of at least one point in time with one or more objects that include properties and values. Visual representation of an object time series may include displaying non-numerical values associated with objects in the object time series in association with respective points in time.

Generation from Abstract Meaning Representation using Tree Transducers

Abstract: Language generation from purely semantic representations is a challenging task. This paper addresses generating English from the Abstract Meaning Representation (AMR), consisting of re-entrant graphs whose nodes are concepts and edges are relations. The new method is trained statistically from AMRannotated English and consists of two major steps: (i) generating an appropriate spanning tree for the AMR, and (ii) applying tree-tostring transducers to generate English. The method relies on discriminative learning and an argument realization model to overcome data sparsity. Initial tests on held-out data show good promise despite the complexity of the task. The system is available open-source as part of JAMR at: http://github.com/jflanigan/jamr

Multi-View 3D Object Retrieval With Deep Embedding Network

Abstract: In multi-view 3D object retrieval, each object is characterized by a group of 2D images captured from different views. Rather than using hand-crafted features, in this paper, we take advantage of the strong discriminative power of convolutional neural network to learn an effective 3D object representation tailored for this retrieval task. Specifically, we propose a deep embedding network jointly supervised by classification loss and triplet loss to map the high-dimensional image space into a low-dimensional feature space, where the Euclidean distance of features directly corresponds to the semantic similarity of images. By effectively reducing the intra-class variations while increasing the inter-class ones of the input images, the network guarantees that similar images are closer than dissimilar ones in the learned feature space. Besides, we investigate the effectiveness of deep features extracted from different layers of the embedding network extensively and find that an efficient 3D object representation should be a tradeoff between global semantic information and discriminative local characteristics. Then, with the set of deep features extracted from different views, we can generate a comprehensive description for each 3D object and formulate the multi-view 3D object retrieval as a set-to-set matching problem. Extensive experiments on SHREC’15 data set demonstrate the superiority of our proposed method over the previous state-of-the-art approaches with over 12% performance improvement.

Scientific Representation Paradoxes Of Perspective

Abstract: scienti?c representation: paradoxes of perspective scientific representation: paradoxes of perspective (review) scientific representation paradoxes of perspective by bas scientific representation paradoxes of perspective eaal scientific representation paradoxes of perspective book of the week: scientific representation: paradoxes of scientific representation: paradoxes of perspective bas c. van fraassen, scientific representation: paradoxes critical notice: bas van fraassen, scientific the journal of philosophy james owen weatherall scientific representation paradoxes of perspective by bas scientific representation paradoxes of perspective by bas scientific representation paradoxes of perspective by bas scientific representation paradoxes of perspective by van scientific representation paradoxes of perspective pdf review: bas van fraassen. scientific representation by bas c van fraassen scientific representation paradoxes scientific representation: paradoxes of perspective by bas review: bas van fraassen’s scienti?c representation introduction. the scientific image

Phonological Representation: Beyond Abstract Versus Episodic

Abstract: Phonological representations capture information about individual word forms and about the general characteristics of word forms in a language. To support the processing of novel word forms as well as familiar word forms in novel contexts, an abstract level of representation is needed in which many phonetic details and contextual features are disregarded. At the same time, evidence has accumulated that such details are retained in memory and used in processing individual words and indexical features of language. Taken together, these results mean that a hybrid model of phonological representation is needed. The abstract level supports generalizations based on lexical type statistics and fast adaptation to communicative requirements through the reuse of existing categories. A richly detailed level of representation is implicated in word-specific phonetic patterns, the detailed dynamics of regular sound changes, and active associations of phonetic patterns with gender, age, and dialect.

Multi-View Object Retrieval via Multi-Scale Topic Models

Abstract: The increasing number of 3D objects in various applications has increased the requirement for effective and efficient 3D object retrieval methods, which attracted extensive research efforts in recent years. Existing works mainly focus on how to extract features and conduct object matching. With the increasing applications, 3D objects come from different areas. In such circumstances, how to conduct object retrieval becomes more important. To address this issue, we propose a multi-view object retrieval method using multi-scale topic models in this paper. In our method, multiple views are first extracted from each object, and then the dense visual features are extracted to represent each view. To represent the 3D object, multi-scale topic models are employed to extract the hidden relationship among these features with respect to varied topic numbers in the topic model. In this way, each object can be represented by a set of bag of topics. To compare the objects, we first conduct topic clustering for the basic topics from two data sets, and then generate the common topic dictionary for new representation. Then, the two objects can be aligned to the same common feature space for comparison. To evaluate the performance of the proposed method, experiments are conducted on two data sets. The 3D object retrieval experimental results and comparison with existing methods demonstrate the effectiveness of the proposed method.

Generic 3D Representation via Pose Estimation and Matching

Abstract: Though a large body of computer vision research has investigated developing generic semantic representations, efforts towards developing a similar representation for 3D has been limited. In this paper, we learn a generic 3D representation through solving a set of foundational proxy 3D tasks: object-centric camera pose estimation and wide baseline feature matching. Our method is based upon the premise that by providing supervision over a set of carefully selected foundational tasks, generalization to novel tasks and abstraction capabilities can be achieved. We empirically show that the internal representation of a multi-task ConvNet trained to solve the above core problems generalizes to novel 3D tasks (e.g., scene layout estimation, object pose estimation, surface normal estimation) without the need for fine-tuning and shows traits of abstraction abilities (e.g., cross modality pose estimation).

On the interpretation and applicability of $\kappa$-distributions

Abstract: The generally accepted representation of $\kappa$-distributions in space plasma physics allows for two different alternatives, namely assuming either the temperature or the thermal velocity to be $\kappa$-independent. The present paper aims to clarify the issue concerning which of the two possible choices and the related physical interpretation is the correct one. A quantitative comparison of the consequences of the use of both distributions for specific physical systems leads to their correct interpretation. It is found that both alternatives can be realized, but are valid for principally different physical systems. The investigation demonstrates that, before employing one of the two alternatives, one should be conscious about the nature of the physical system one intends to describe, otherwise one would possibly obtain unphysical results.

Active tactile object exploration with Gaussian processes

Abstract: Accurate object shape knowledge provides important information for performing stable grasping and dexterous manipulation. When modeling an object using tactile sensors, touching the object surface at a fixed grid of points can be sample inefficient. In this paper, we present an active touch strategy to efficiently reduce the surface geometry uncertainty by leveraging a probabilistic representation of object surface. In particular, we model the object surface using a Gaussian process and use the associated uncertainty information to efficiently determine the next point to explore. We validate the resulting method for tactile object surface modeling using a real robot to reconstruct multiple, complex object surfaces.

The Fiction View of Models Reloaded

Abstract: In this paper we explore the constraints that our preferred account of scientific representation places on the ontology of scientific models. Pace the Direct Representation view associated with Arnon Levy and Adam Toon we argue that scientific models should be thought of as imagined systems, and clarify the relationship between imagination and representation.

Displaying Loot. The Benin objects and the British Museum

Abstract: Ph.D. dissertation at University of Gothenburg, Sweden, 2016 Title: Displaying Loot: The Benin Objects and the British Museum Author: Staffan Lundén Language: English Department: Department of Historical Studies, University of Gothenburg, Box 200, SE-405 30, Gothenburg. ISBN: 978-91-85245-67-4 ISSN: 0282-6860 Displaying Loot. The Benin Objects and the British Museum This study deals with the objects, now in the British Museum, that were looted from Benin City, present-day Nigeria, in 1897. It looks at how the museum represents the Benin objects, the Edo/African, the British/Westerner, and the British Museum. According to the museum, the Benin objects provide the “key argument” against the return of objects in its collections. The study pays particular attention to how the museum’s representations relate to its retentionist argument. The museum maintains that it was founded to foster tolerance, dissent, and respect for difference, and that it today shows many different cultures without privileging any of them. The museum’s benevolent impact is exemplified by the Benin objects whose arrival in the West has led to the shattering of European derogatory stereotypes of Africans, thanks to British Museum scholars. The study examines these claims and finds that they rest on flimsy or no evidence. The museum misrepresents and glorifies its own past and exaggerates its own contribution to Benin scholarship and the European view of Africans. The museum has shown cultures, not as equal, but as placed in a hierarchy, and in the early 20th century its scholars gave scientific legitimization to the stock stereotypes of Africans, such as the likening of Blacks to apes. The analysis of the museum’s contemporary exhibition and accompanying publications show that the museum – still – represents self and other as different: the Edo/African is portrayed as traditional while the Westerner is portrayed as progressive. The study concludes that, despite the museum’s claim to universality, its representations are deeply enmeshed in, and shaped by, British (museum) traditions and cultural assumptions. Paradoxically, while the statement of objectivity and impartiality is central to the museum’s defense against claims, it seems that the ownership issue strongly contributes to the biases in its representations.

Single-Model Encoder-Decoder with Explicit Morphological Representation for Reinflection

Abstract: Morphological reinflection is the task of generating a target form given a source form, a source tag and a target tag. We propose a new way of modeling this task with neural encoder-decoder models. Our approach reduces the amount of required training data for this architecture and achieves state-of-the-art results, making encoder-decoder models applicable to morphological reinflection even for lowresource languages. We further present a new automatic correction method for the outputs based on edit trees.

Linking somatic and symbolic representation in semantic memory: the dynamic multilevel reactivation framework.

Abstract: Biological plausibility is an essential constraint for any viable model of semantic memory. Yet, we have only the most rudimentary understanding of how the human brain conducts abstract symbolic transformations that underlie word and object meaning. Neuroscience has evolved a sophisticated arsenal of techniques for elucidating the architecture of conceptual representation. Nevertheless, theoretical convergence remains elusive. Here we describe several contrastive approaches to the organization of semantic knowledge, and in turn we offer our own perspective on two recurring questions in semantic memory research: (1) to what extent are conceptual representations mediated by sensorimotor knowledge (i.e., to what degree is semantic memory embodied)? (2) How might an embodied semantic system represent abstract concepts such as modularity, symbol, or proposition? To address these questions, we review the merits of sensorimotor (i.e., embodied) and amodal (i.e., disembodied) semantic theories and address the neurobiological constraints underlying each. We conclude that the shortcomings of both perspectives in their extreme forms necessitate a hybrid middle ground. We accordingly propose the Dynamic Multilevel Reactivation Framework—an integrative model predicated upon flexible interplay between sensorimotor and amodal symbolic representations mediated by multiple cortical hubs. We discuss applications of the dynamic multilevel reactivation framework to abstract and concrete concept representation and describe how a multidimensional conceptual topography based on emotion, sensation, and magnitude can successfully frame a semantic space containing meanings for both abstract and concrete words. The consideration of ‘abstract conceptual features’ does not diminish the role of logical and/or executive processing in activating, manipulating and using information stored in conceptual representations. Rather, it proposes that the materials upon which these processes operate necessarily combine pure sensorimotor information and higher-order cognitive dimensions involved in symbolic representation.

The Representation of Object-Directed Action and Function Knowledge in the Human Brain

Abstract: The appropriate use of everyday objects requires the integration of action and function knowledge. Previous research suggests that action knowledge is represented in frontoparietal areas while function knowledge is represented in temporal lobe regions. Here we used multivoxel pattern analysis to investigate the representation of object-directed action and function knowledge while participants executed pantomimes of familiar tool actions. A novel approach for decoding object knowledge was used in which classifiers were trained on one pair of objects and then tested on a distinct pair; this permitted a measurement of classification accuracyoverand above object-specific information. Region of interest (ROI) analyses showed that object-directed actions could be decoded in tool-preferring regions of both parietal and temporal cortex, while no independently defined toolpreferring ROI showed successful decoding of object function. However, a whole-brain searchlight analysis revealed that while frontoparietal motorand peri-motor regions are engaged in the representation of object-directed actions, medial temporal lobe areas in the left hemisphere are involved in the representation of function knowledge. These results indicate that both action and function knowledge are represented in a topographically coherent manner that is amenable to study with multivariate approaches, and that the left medial temporal cortex represents knowledge of object function.