Object (computer science)

About: Object (computer science) is a research topic. Over the lifetime, 106024 publications have been published within this topic receiving 1360115 citations. The topic is also known as: obj & Rq.

A network that learns to recognize three-dimensional objects.

Abstract: THE visual recognition of three-dimensional (3-D) objects on the basis of their shape poses at least two difficult problems. First, there is the problem of variable illumination, which can be addressed by working with relatively stable features such as intensity edges rather than the raw intensity images1,2. Second, there is the problem of the initially unknown pose of the object relative to the viewer. In one approach to this problem, a hypothesis is first made about the viewpoint, then the appearance of a model object from such a viewpoint is computed and compared with the actual image3–7. Such recognition schemes generally employ 3-D models of objects, but the automatic learning of 3-D models is itself a difficult problem8,9. To address this problem in computational vision, we have developed a scheme, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view. A network equivalent to this scheme will thus 'recognize' the object on which it was trained from any viewpoint.

A Framework for Generating Network-Based Moving Objects

Abstract: Benchmarking spatiotemporal database systems requires the definition of suitable datasets simulating the typical behavior of moving objects. Previous approaches for generating spatiotemporal data do not consider that moving objects often follow a given network. Therefore, benchmarks require datasets consisting of such “network-based” moving objects. In this paper, the most important properties of network-based moving objects are presented and discussed. Essential aspects are the maximum speed and the maximum capacity of connections, the influence of other moving objects on the speed and the route of an object, the adequate determination of the start and destination of an object, the influence of external events, and time-scheduled traffic. These characteristics are the basis for the specification and development of a new generator for spatiotemporal data. This generator combines real data (the network) with user-defined properties of the resulting dataset. A framework is proposed where the user can control the behavior of the generator by re-defining the functionality of selected object classes. An experimental performance investigation demonstrates that the chosen approach is suitable for generating large data sets.

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

Abstract: Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use self-attention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar (Object-Semantics Aligned Pre-training), which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation that the salient objects in an image can be accurately detected, and are often mentioned in the paired text. We pre-train an Oscar model on the public corpus of 6.5 million text-image pairs, and fine-tune it on downstream tasks, creating new state-of-the-arts on six well-established vision-language understanding and generation tasks.

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

Abstract: We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets. The benefits of our model are three-fold: first, the use of an adversarial criterion, instead of traditional heuristic criteria, enables the generator to capture object structure implicitly and to synthesize high-quality 3D objects; second, the generator establishes a mapping from a low-dimensional probabilistic space to the space of 3D objects, so that we can sample objects without a reference image or CAD models, and explore the 3D object manifold; third, the adversarial discriminator provides a powerful 3D shape descriptor which, learned without supervision, has wide applications in 3D object recognition. Experiments demonstrate that our method generates high-quality 3D objects, and our unsupervisedly learned features achieve impressive performance on 3D object recognition, comparable with those of supervised learning methods.

“What” and “where” in spatial language and spatial cognition

Abstract: Fundamental to spatial knowledge in all species are the representations underlying object recognition, object search, and navigation through space. But what sets humans apart from other species is our ability to express spatial experience through language. This target article explores the language of objects and places, asking what geometric properties are preserved in the representations underlying object nouns and spatial prepositions in English. Evidence from these two aspects of language suggests there are significant differences in the geometric richness with which objects and places are encoded. When an object is named (i.e., with count nouns), detailed geometric properties – principally the object's shape (axes, solid and hollow volumes, surfaces, and parts) – are represented. In contrast, when an object plays the role of either “figure” (located object) or “ground” (reference object) in a locational expression, only very coarse geometric object properties are represented, primarily the main axes. In addition, the spatial functions encoded by spatial prepositions tend to be nonmetric and relatively coarse, for example, “containment,” “contact,” “relative distance,” and “relative direction.” These properties are representative of other languages as well. The striking differences in the way language encodes objects versus places lead us to suggest two explanations: First, there is a tendency for languages to level out geometric detail from both object and place representations. Second, a nonlinguistic disparity between the representations of “what” and “where” underlies how language represents objects and places. The language of objects and places converges with and enriches our understanding of corresponding spatial representations.