Scene Interpretation Research Articles

Anna Karenina Reads on the Train: Readerly Subjectivity and the Poetics of the Novel

What does it mean to be a reader of a novel? he famous scene of Anna Karenina reading on the train takes up this question. Whereas Tolstoy's scene is traditionally viewed as yet another example of the pleasures and dangers of novel reading, from empathic identiication to romantic self-aestheticization, I argue that the scene investigates the phenomenology of novel reading, the nature of readerly subjectivity, and the poetics of the classic realist novel—all in ways that depart from other canonical literary depictions of novel reading. Bringing together the poetics of the realist novel with complex issues of selfknowledge and deliberation, the scene reveals a new form of readerly subjectivity that entails the imagined nonexistence of the empirical reader. Drawing on Bakhtin, Kierkegaard, Sartre, and others, I show the implications of this form of readerly subjectivity for not only an original interpretation of Tolstoy's much-read scene but also our understanding of novel reading.

Effects of Post-Event Processing on interpretation and anxiety of social scene

Effects of Post-Event Processing on interpretation and anxiety of social scene

INDOOR MESH CLASSIFICATION FOR BIM

Abstract. This work addresses the automatic reconstruction of objects useful for BIM, like walls, floors and ceilings, from meshed and textured mapped 3D point clouds of indoor scenes. For this reason, we focus on the semantic segmentation of 3D indoor meshes as the initial step for the automatic generation of BIM models. Our investigations are based on the benchmark dataset ScanNet, which aims at the interpretation of 3D indoor scenes. For this purpose it provides 3D meshed representations as collected from low cost range cameras. In our opinion such RGB-D data has a great potential for the automated reconstruction of BIM objects.

O espectador-transeunte: momentos de suspensão da vida cotidiana

O texto analisa a proposta cênica “Transeuntes”, realizada em um terminal de ônibus, que propôs como procedimento cênico o encontro/desvio dos pedestres, interações com os espectadores previamente convidados e dinâmicas estabelecidas com o espaço urbano. Em um ambiente onde concorrem outras ações adjacentes, é solicitada do público a construção dinâmica de interpretação da cena mesclada à vida cotidiana. Desse modo, o espectador, enquanto observante/partícipe, escolhe o que irá ver, realiza cortes e edita, estabelecendo uma percepção seletiva.

Egocentric visual scene description based on human-object interaction and deep spatial relations among objects

Visual Scene interpretation is one of the major areas of research in the recent past. Recognition of human object interaction is a fundamental step towards understanding visual scenes. Videos can be described via a variety of human-object interaction scenarios such as when both human and object are static (static-static), one is static while other is dynamic (static-dynamic) and both are dynamic (dynamic-dynamic). This paper presents a unified framework for the explanation of these interactions between humans and a variety of objects using deep learning as a pivot methodology. Human-object interaction is extracted through native machine learning techniques, while spatial relations are captured by training a model through convolution neural network. We also address the recognition of human posture in detail to provide egocentric visual description. After extracting visual features, sequential minimal optimization is employed for training our model. Extracted inter-action, spatial relations and posture information are fed into natural language generation module along with interacting object label to generate scene understanding. Evaluation of the proposed framework is done for two state of the art datasets i.e., MSCOCO and MSR3D Daily activity dataset; where achieved results are 78 and 91.16% accurate, respectively.

Multidimensional brain activity dictated by winner-take-all mechanisms

A novel demon-based architecture is introduced to elucidate brain functions such as pattern recognition during human perception and mental interpretation of visual scenes. Starting from the topological concepts of invariance and persistence, we introduce a Selfridge pandemonium variant of brain activity that takes into account a novel feature, namely, demons that recognize short straight-line segments, curved lines and scene shapes, such as shape interior, density and texture. Low-level representations of objects can be mapped to higher-level views (our mental interpretations): a series of transformations can be gradually applied to a pattern in a visual scene, without affecting its invariant properties. This makes it possible to construct a symbolic multi-dimensional representation of the environment. These representations can be projected continuously to an object that we have seen and continue to see, thanks to the mapping from shapes in our memory to shapes in Euclidean space. Although perceived shapes are 3-dimensional (plus time), the evaluation of shape features (volume, color, contour, closeness, texture, and so on) leads to n-dimensional brain landscapes. Here we discuss the advantages of our parallel, hierarchical model in pattern recognition, computer vision and biological nervous system’s evolution.

A Survey of Scene Understanding by Event Reasoning in Autonomous Driving

Realizing autonomy is a hot research topic for automatic vehicles in recent years. For a long time, most of the efforts to this goal concentrate on understanding the scenes surrounding the ego-vehicle (autonomous vehicle itself). By completing low-level vision tasks, such as detection, tracking and segmentation of the surrounding traffic participants, e.g., pedestrian, cyclists and vehicles, the scenes can be interpreted. However, for an autonomous vehicle, low-level vision tasks are largely insufficient to give help to comprehensive scene understanding. What are and how about the past, the on-going and the future of the scene participants? This deep question actually steers the vehicles towards truly full automation, just like human beings. Based on this thoughtfulness, this paper attempts to investigate the interpretation of traffic scene in autonomous driving from an event reasoning view. To reach this goal, we study the most relevant literatures and the state-of-the-arts on scene representation, event detection and intention prediction in autonomous driving. In addition, we also discuss the open challenges and problems in this field and endeavor to provide possible solutions.

VidOnt: a core reference ontology for reasoning over video scenes

ABSTRACTThe conceptualization of domains depicted in videos is a necessary, but not sufficient requirement for reasoning-based high-level scene interpretation, which requires the formal representation of the timeline structure, the moving regions of interest, and video production standards, facilities, and procedures as well. Multimedia ontologies, including the very few video ontologies, however, are not exhaustive in terms of concept coverage, redefine terms against Semantic Web best practices, are not aligned with standards, and do not define complex roles and role interdependencies. Because most multimedia ontologies implement only a minimal subset of the mathematical constructors of OWL, and define a TBox and an ABox, but not an RBox, they do not support complex inferencing. This paper describes a formally grounded core reference ontology for video representation, which addresses many of these issues and limitations.

The use of rapid identification information at the crime scene; similarities and differences between English and Dutch CSIs

ABSTRACTThis study replicates previous research that investigated the influence of rapid identification information on the interpretation of a crime scene conducted with English crime scene investigators (CSIs). Given the special circumstances under which CSIs in one country operate, the present study investigates the robustness and generalisability of the previous findings by studying whether identical decision-making phenomena are found in a replication study within a different police environment. Dutch CSIs (N = 65) participated in the same study and results are compared with the English findings. The utility of the replication study is reflected in both the revealed robustness and differences in the findings. First, the results demonstrate the robustness of the previous finding that ID information influenced the interpretation of the crime scene, even more when this information was provided after CSIs had constructed a provisional scenario. Secondly, this study revealed differences in decision-making: English CSIs used ID information to make efficient decisions by prioritising traces with direct progression opportunities for the case and disregarding those without direct opportunities, which led to a form of tunnel vision, namely the ignorance of the involvement of a second offender. Dutch CSIs showed to be less prone to bias towards traces that produced database matches. Dutch CSIs seemed to be more focused on the relation of the trace with the crime, while English CSIs are more focused on the database match. Consequently, important information was overlooked. We question whether the emphasis on efficiency in England goes at the expense of the quality of an investigation.

The application of scenario simulation in the class teaching of management secretary practice for health management specialty

In order to help students to apply theory to practice and improve their ability of problem-solving, the scenario simulation was applied to the class teaching of management secretary practice for health management specialty. Itiscomposed of three phrases: task allocation, and material preparation, basic background and scene interpretation and evaluation. The scenario simulation is able to combine and deduce the knowledge by simulating such scenes as office work, meeting room and unexcepted incidents, which can help student to consolidate knowledge and enhance their team spirit and participating awareness. Meanwhile, teachers can better realize the teaching objectives through interesting class teaching. Key words: Health management; Scenario simulation; Teaching methods

Solving the puzzle: The effects of contextual information and feedback on the interpretation of a crime scene

AbstractIn this study, we examined how the provision of contextual information and the ability to ask questions and obtain feedback affected mock investigators' interpretation of a crime scene. Participants were randomly assigned to 1 of 4 conditions in a 2 × 2 design and assessed two photographs of the same crime scene. Participants were instructed to write a narrative about what they thought had happened at the scene. Results showed that the provision of contextual information and the ability to ask questions had no effect on the lengths of the narratives participants produced. However, participants who received contextual information wrote a more factual narrative containing more descriptions of actions before, during, and after the crime. Across all conditions, most of the questions were asked about persons who could in some way be involved in the crime. Results of this study indicate that the provision of contextual information helped participants to focus on the more factual, rather than speculative elements, of the crime.

Video scene analysis: an overview and challenges on deep learning algorithms

Video scene analysis is a recent research topic due to its vital importance in many applications such as real-time vehicle activity tracking, pedestrian detection, surveillance, and robotics. Despite its popularity, the video scene analysis is still an open challenging task and require more accurate algorithms. However, the advances in deep learning algorithms for video scene analysis have been emerged in last few years for solving the problem of real-time processing. In this paper, a review of the recent developments in deep learning and video scene analysis problems is presented. In addition, this paper also briefly describes the most recent used datasets along with their limitations. Moreover, this review provides a detailed overview of the particular challenges existed in real-time video scene analysis that has been contributed towards activity recognition, scene interpretation, and video description/captioning. Finally, the paper summarizes the future trends and challenges in video scene analysis tasks and our insights are provided to inspire further research efforts.

Motion of glossy objects does not promote separation of lighting and surface colour.

The surface properties of an object, such as texture, glossiness or colour, provide important cues to its identity. However, the actual visual stimulus received by the eye is determined by both the properties of the object and the illumination. We tested whether operational colour constancy for glossy objects (the ability to distinguish changes in spectral reflectance of the object, from changes in the spectrum of the illumination) was affected by rotational motion of either the object or the light source. The different chromatic and geometric properties of the specular and diffuse reflections provide the basis for this discrimination, and we systematically varied specularity to control the available information. Observers viewed animations of isolated objects undergoing either lighting or surface-based spectral transformations accompanied by motion. By varying the axis of rotation, and surface patterning or geometry, we manipulated: (i) motion-related information about the scene, (ii) relative motion between the surface patterning and the specular reflection of the lighting, and (iii) image disruption caused by this motion. Despite large individual differences in performance with static stimuli, motion manipulations neither improved nor degraded performance. As motion significantly disrupts frame-by-frame low-level image statistics, we infer that operational constancy depends on a high-level scene interpretation, which is maintained in all conditions.

A recurrent neural model for proto-object based contour integration and figure-ground segregation.

Visual processing of objects makes use of both feedforward and feedback streams of information. However, the nature of feedback signals is largely unknown, as is the identity of the neuronal populations in lower visual areas that receive them. Here, we develop a recurrent neural model to address these questions in the context of contour integration and figure-ground segregation. A key feature of our model is the use of grouping neurons whose activity represents tentative objects ("proto-objects") based on the integration of local feature information. Grouping neurons receive input from an organized set of local feature neurons, and project modulatory feedback to those same neurons. Additionally, inhibition at both the local feature level and the object representation level biases the interpretation of the visual scene in agreement with principles from Gestalt psychology. Our model explains several sets of neurophysiological results (Zhou et al. Journal of Neuroscience, 20(17), 6594-6611 2000; Qiu et al. Nature Neuroscience, 10(11), 1492-1499 2007; Chen et al. Neuron, 82(3), 682-694 2014), and makes testable predictions about the influence of neuronal feedback and attentional selection on neural responses across different visual areas. Our model also provides a framework for understanding how object-based attention is able to select both objects and the features associated with them.

POINT CLOUD ANALYSIS FOR UAV-BORNE LASER SCANNING WITH HORIZONTALLY AND VERTICALLY ORIENTED LINE SCANNERS – CONCEPT AND FIRST RESULTS

Abstract. In this paper, we focus on UAV-borne laser scanning with the objective of densely sampling object surfaces in the local surrounding of the UAV. In this regard, using a line scanner which scans along the vertical direction and perpendicular to the flight direction results in a point cloud with low point density if the UAV moves fast. Using a line scanner which scans along the horizontal direction only delivers data corresponding to the altitude of the UAV and thus a low scene coverage. For these reasons, we present a concept and a system for UAV-borne laser scanning using multiple line scanners. Our system consists of a quadcopter equipped with horizontally and vertically oriented line scanners. We demonstrate the capabilities of our system by presenting first results obtained for a flight within an outdoor scene. Thereby, we use a downsampling of the original point cloud and different neighborhood types to extract fundamental geometric features which in turn can be used for scene interpretation with respect to linear, planar or volumetric structures.

Multi-inducer grouping for curve completion: Perceptual and computational exploration.

The human visual system excels in object recognition and scene interpretation even in scenes in which some (or even all) observed objects are partially occluded or fragmented. This highly efficient capacity is facilitated by constructive processes of contour completion between inducers to yield the perception of whole objects across gaps. A fundamental problem of the process is when and how the visual system groups different inducers in the visual scene between which completion occurs. Previous studies on this grouping problem, inspired mostly by relatability theory (Kellman & Shipley, 1991), focused on one good continuation condition that dictates whether a given pair of inducers would group together or not. Left open, however, was the question of how good continuation interacts with other grouping factors and how the perceptual system groups inducers when more than two of them are present in a scene (as would be in most typical natural stimuli). Here, we address both issues by exploring observers' perceptual response in multi-inducer scenes in which inducers and their relationships are determined by three independent factors: relative proximity, relative orientation, and curvature. Employing the dot localization paradigm, we indirectly inferred the type of inducer grouping constructed by the observer's visual system and analyzed the three-dimensional response function. Furthermore, we propose a simple parametric model that suggests an opponency relationship between two of the grouping factors and predicts subject's likely response with high accuracy. We also analyzed the discrepancy between our results and model the predictions made by the classical relatability theory.

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

Segmentation techniques play an important role in understanding high-resolution polarimetric synthetic aperture radar (PolSAR) images. PolSAR image segmentation is widely used as a preprocessing step for subsequent classification, scene interpretation and extraction of surface parameters. However, speckle noise and rich spatial features of heterogeneous regions lead to blurred boundaries of high-resolution PolSAR image segmentation. A novel segmentation algorithm is proposed in this study in order to address the problem and to obtain accurate and precise segmentation results. This method integrates statistical features into a fractal net evolution algorithm (FNEA) framework, and incorporates polarimetric features into a simple linear iterative clustering (SLIC) superpixel generation algorithm. First, spectral heterogeneity in the traditional FNEA is substituted by the G0 distribution statistical heterogeneity in order to combine the shape and statistical features of PolSAR data. The statistical heterogeneity between two adjacent image objects is measured using a log likelihood function. Second, a modified SLIC algorithm is utilized to generate compact superpixels as the initial samples for the G0 statistical model, which substitutes the polarimetric distance of the Pauli RGB composition for the CIELAB color distance. The segmentation results were obtained by weighting the G0 statistical feature and the shape features, based on the FNEA framework. The validity and applicability of the proposed method was verified with extensive experiments on simulated data and three real-world high-resolution PolSAR images from airborne multi-look ESAR, spaceborne single-look RADARSAT-2, and multi-look TerraSAR-X data sets. The experimental results indicate that the proposed method obtains more accurate and precise segmentation results than the other methods for high-resolution PolSAR images.

Learning from label proportions for SAR image classification

Synthetic aperture radar (SAR) image classification plays a key role in SAR interpretation. Due to the cost and difficulty of truth labeling for SAR images, the newly labeled samples available for image classification are very limited. This paper focuses on defining a new sample labeling method to solve the problem of truth acquisition for training data in SAR image classification. An efficient classification framework for high-resolution SAR images is presented in this paper, which is built on learning from uncertain labels. We use grid labeling for rapid training data acquisition by assigning a label to a group of neighboring pixels at a time. A novel SVM-based learning model is proposed to optimize the uncertain training data within the constraints of label proportions in each group and then predict the label of each sample for the test data based on the optimized training set. This work intends to explore a rapid labeling method called grid labeling for efficient training set definition and apply it to large-scale SAR image classification. The model demonstrates good performance in both accuracy and efficiency for scene interpretation of high-resolution SAR images.

Rapid identification information and its influence on the perceived clues at a crime scene: An experimental study

Crime scenes can always be explained in multiple ways. Traces alone do not provide enough information to infer a whole series of events that has taken place; they only provide clues for these inferences. CSIs need additional information to be able to interpret observed traces. In the near future, a new source of information that could help to interpret a crime scene and testing hypotheses will become available with the advent of rapid identification techniques. A previous study with CSIs demonstrated that this information had an influence on the interpretation of the crime scene, yet it is still unknown what exact information was used for this interpretation and for the construction of their scenario. The present study builds on this study and gains more insight into (1) the exact investigative and forensic information that was used by CSIs to construct their scenario, (2) the inferences drawn from this information, and (3) the kind of evidence that was selected at the crime scene to (dis)prove this scenario. We asked 48 CSIs to investigate a potential murder crime scene on the computer and explicate what information they used to construct a scenario and to select traces for analysis. The results show that the introduction of rapid ID information at the start of an investigation contributes to the recognition of different clues at the crime scene, but also to different interpretations of identical information, depending on the kind of information available and the scenario one has in mind. Furthermore, not all relevant traces were recognized, showing that important information can be missed during the investigation. In this study, accurate crime scenarios where mainly build with forensic information, but we should be aware of the fact that crime scenes are always contaminated with unrelated traces and thus be cautious of the power of rapid ID at the crime scene.

Identification at the crime scene: The sooner, the better? The interpretation of rapid identification information by CSIs at the crime scene

New technologies will allow Crime Scene Investigators (CSIs) in the near future to analyse traces at the crime scene and receive identification information while still conducting the investigation. These developments could have considerable effects on the way an investigation is conducted. CSIs may start reasoning based on possible database-matches which could influence scenario formation (i.e. the construction of narratives that explain the observed traces) during very early phases of the investigation. The goal of this study is to gain more insight into the influence of the rapid identification information on the reconstruction of the crime and the evaluation of traces by addressing two questions, namely 1) is scenario formation influenced from the moment that ID information is provided and 2) do database matches influence the evaluation of traces and the reconstruction of the crime. We asked 48 CSIs from England to investigate a potential murder crime scene on a computer. Our findings show that the interpretation of the crime scene by CSIs is affected by the moment identification information is provided. This information has a higher influence on scenario formation when provided after an initial scenario has been formed. Also, CSIs seem to attach great value to traces that produce matches with databases and hence yield a name of a known person. Similar traces that did not provide matches were considered less important. We question whether this kind of selective attention is desirable as it may cause ignorance of other relevant information at the crime scene.