Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 31 for “"Scene Graphs"”.

  1. Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs

    … et al. [7]. The query is structured as a scene graph and a graphical model is generated from the scene graph's object, attribute, and relationship structure. Inference is performed on the graphical model with candidate images and the energy results are used to rank the best matches. In …

    portland-state Repository record for Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs (opens in a new tab)

  2. A network design architecture for distribution of generic scene graphs

    … project examines a new approach: using generic scene graphs as a bus, for graphics distribution. This thesis (as part of the SOFT project) examines network architecture for distribution of generic scene graphs. We design and implement the network architecture with a centralized Java server. This …

    nps Repository record for A network design architecture for distribution of generic scene graphs (opens in a new tab)

  3. Discourse-guided text-generation from knowledge graphs and image scene graphs

    … text from semi-structured data - knowledge graphs and image scene graphs. We provide a novel architecture that integrates discourse planning as an intermediary structuring step, with the objective of enhancing coherence, readability, and the overall quality of generated content. The proposed …

    ubc Repository record for Discourse-guided text-generation from knowledge graphs and image scene graphs (opens in a new tab) Download PDF for Discourse-guided text-generation from knowledge graphs and image scene graphs (opens in a new tab)

  4. STRUCTURED MULTIMODAL INTELLIGENCE: SCENE GRAPHS FOR VISION-LANGUAGE UNDERSTANDING, GENERATION, AND UNIFICATION

    … linguistic descriptions. This thesis proposes a scene graph–empowered modeling paradigm that introduces structured semantic representations as a unifying abstraction for V–L learning. First, for fine-grained understanding, both visual and textual inputs are represented as scene graphs, enabling …

    nus Repository record for STRUCTURED MULTIMODAL INTELLIGENCE: SCENE GRAPHS FOR VISION-LANGUAGE UNDERSTANDING, GENERATION, AND UNIFICATION (opens in a new tab) Download file for STRUCTURED MULTIMODAL INTELLIGENCE: SCENE GRAPHS FOR VISION-LANGUAGE UNDERSTANDING, GENERATION, AND UNIFICATION (opens in a new tab)

  5. Scene Graph Memory Management

    … This thesis studies the effects of data layout on scene graphs, a common data structure for organising scenes in graphics applications. Specifically, it studies (1) which way of packing nodes in memory yield the best performance for typical scene graph traversal patterns, and (2) proposes a novel …

    chalmers Repository record for Scene Graph Memory Management (opens in a new tab)

  6. Open-Vocabulary Scene Graph Generation With Compositional Prompt-Tuning

    Scene graphs are explicit data structures that express the semantics of an image. It is semantically richer than simple image encodings from Convolutional Neural Networks (CNNs) because objects (big or small) are represented as distinct nodes and the relationship between them are expressed as …

    uab Repository record for Open-Vocabulary Scene Graph Generation With Compositional Prompt-Tuning (opens in a new tab)

  7. Comparison of Vega tm an JAVA3D tm in a virtual environment enclosure

    … improve presence for a number of applications. Scene graphs are accepted as the logical and optimized way to generate and render applications, however most scene graphs are proprietary or platform specific. Open source scene graphs are emerging that are easily used and cross- platform. This …

    nps Repository record for Comparison of Vega tm an JAVA3D tm in a virtual environment enclosure (opens in a new tab)

  8. Assessing and Improving Generalization in Graph Reasoning and Learning

    … task of parameter prediction for neural network graphs. In the first article we study the attention mechanism in graph neural networks (GNNs). While attention has been widely studied in GNNs, its effect on generalization to larger and noisier graphs has not been thoroughly analyzed. We show that …

    guelph Repository record for Assessing and Improving Generalization in Graph Reasoning and Learning (opens in a new tab)

  9. Representation Learning for Interpretation of Chest X-rays

    … a subset of MIMICCXR, which comprises 242,072 scene graphs that describe individual chest X-rays. These scene graphs contain automatically extracted information from radiology reports, including patient demographics, anatomical bounding boxes, pathological findings, and progression of disease …

    mcmaster Repository record for Representation Learning for Interpretation of Chest X-rays (opens in a new tab)

  10. Data-efficient learning on structured output data

    … scribbles, bounding boxes, segmentation masks to scene-graphs. Efficient learning approaches attempts to alleviate this issue by utilizing lower quantity (em e.g., few-shot learning) and quality (em e.g., weakly-supervised learning) of annotations for a target task. In this thesis, we explore and …

    ubc Repository record for Data-efficient learning on structured output data (opens in a new tab) Download PDF for Data-efficient learning on structured output data (opens in a new tab)

  11. Scene Understanding and Spatial Analysis Using Scene Graph Enhanced by Hall's Proxemics Zones in Smart Homes

    … and intuitive automation in smart homes. I apply scene graphs to provide a structured representation, such as positions, relationships, and properties, of the static and moving objects in indoor home environments. The novelty of this approach lies in the application of proxemics via scene graph …

    mo-state Repository record for Scene Understanding and Spatial Analysis Using Scene Graph Enhanced by Hall's Proxemics Zones in Smart Homes (opens in a new tab)

  12. Learning multiple solutions to computer vision problems

    … such as image colorization, image captioning and scene-graph prediction. Our strategy to generate multiple solutions is as follows – (i) We first generate multiple proposals given the input image. These proposals are not to be confused with the object or region proposals of detection networks. Our …

    uiuc Repository record for Learning multiple solutions to computer vision problems (opens in a new tab)

  13. Hermes: Heterogeneous Edge-Relational Multi-Head SSM-Embedded Attention for Traffic Conflict Prediction at Signalized Intersections

    … dynamics of full multi-agent intersection scenes. This study addresses this gap by formulating traffic conflict anticipation as a scene-level graph classification problem and proposes HERMES, a heterogeneous edge-relational graph neural framework with multi-head SSM-embedded attention. In …

    texas-state Repository record for Hermes: Heterogeneous Edge-Relational Multi-Head SSM-Embedded Attention for Traffic Conflict Prediction at Signalized Intersections (opens in a new tab)

  14. Generative modeling of topological and spatiotemporal data

    … not present in flat vectors or single images: graphs are invariant to node ordering, visual scenes combine symbolic relations with continuous geometry, and human or driving motion evolves through interacting agents under uncertainty. This dissertation develops generative models for topological, …

    ubc Repository record for Generative modeling of topological and spatiotemporal data (opens in a new tab) Download PDF for Generative modeling of topological and spatiotemporal data (opens in a new tab)

  15. Scenario Extraction from Egocentric Automotive Datasets

    … We represent a driving scenario by a sequence of scene graphs, which are a structured semantic representation of a scene. Next, we formally define driving scenarios of interest using Linear Temporal Logic (LTL), then extract all instances of the scenarios from the dataset using an off-the-shelf …

    mcmaster Repository record for Scenario Extraction from Egocentric Automotive Datasets (opens in a new tab)

  16. Understanding visual and linguistic content by structured representations

    … may fail to fully capture the complex details of scenes involving multiple objects and their relationships. To spur research in this field, this dissertation explores the use of structured representations in visual and linguistic content, aiming for a comprehensive and precise understanding of …

    bu Repository record for Understanding visual and linguistic content by structured representations (opens in a new tab)

  17. Grounding Perception and Reasoning in Multimodal Models

    … Genome, a method for scaling up structured scene graphs defined by objects and their relationships. By distilling this structural knowledge into the training process, I show that this approach significantly improves grounded relationship understanding and reasoning.

    washington Repository record for Grounding Perception and Reasoning in Multimodal Models (opens in a new tab)

  18. Situate: An Agent-Based System for Situation Recognition

    … as to a related image-retrieval system based on "scene graphs". I will evaluate each method on the situation recognition task and in the context of image retrieval. The results demonstrate the value of a feedback system between image content and a model of that content.

    portland-state Repository record for Situate: An Agent-Based System for Situation Recognition (opens in a new tab)

  19. Human-Centered Explainable AI for Sequential Decision-Making Systems

    … that extracts environmental-context via semantic scene graphs to provide scalable explanations of robot failures; (4) an algorithm that explains suboptimal, hierarchical AI systems by extracting appropriate subgoal information to help users avoid suboptimal decisions; (5) a framework that …

    gatech Repository record for Human-Centered Explainable AI for Sequential Decision-Making Systems (opens in a new tab)

  20. Spatiotemporal Event Graphs for Dynamic Scene Understanding

    Dynamic scene understanding is the ability of a computer system to interpret and make sense of the visual information present in a video of a real-world scene. In this thesis, we present a series of frameworks for dynamic scene understanding starting from road event detection from an autonomous …

    oxford-brookes Repository record for Spatiotemporal Event Graphs for Dynamic Scene Understanding (opens in a new tab) Download PDF for Spatiotemporal Event Graphs for Dynamic Scene Understanding (opens in a new tab)

Page 1 of 2