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 51 for “"Visual Reasoning"”.

  1. Extracting, predicting, and explaining human visual reasoning

    … high-level analytic tasks through sophisticated visual reasoning processes. While eye-tracking studies have revealed important behavioral patterns and modern deep learning models have achieved impressive predictive performance, an important scientific gap remains: current AI systems have limited …

    missouri Repository record for Extracting, predicting, and explaining human visual reasoning (opens in a new tab) Embargoed until 2026-12-01

  2. 3D VISUAL REASONING FOR ROBUST AUTONOMOUS DRIVING SYSTEMS

    Perception and visual reasoning models are crucial components of autonomous driving systems. Having a good understanding of the surrounding environment enables these systems to make accurate decisions. 3D visual data is a rich source of information about the world around us, making it extremely …

    jhu Repository record for 3D VISUAL REASONING FOR ROBUST AUTONOMOUS DRIVING SYSTEMS (opens in a new tab)

  3. On the Diagnosis and Generalization of Compositional Visual Reasoning

    Computer vision is not only about recognizing visual signals, but also rea- soning over perceived visual elements. This ability, termed visual reasoning, is typically studied by multimodal tasks like visual question answering and image captioning. Thanks to recent developments in multimodal …

    jhu Repository record for On the Diagnosis and Generalization of Compositional Visual Reasoning (opens in a new tab)

  4. Integrating Knowledge Into Visual Reasoning: Enhancing Generalizability, Explainability, And Bias Mitigation

    The ability to reason about the complexity of visual world is one type of fundamental artificial intelligence (AI). Advances in large-scale datasets and visual reasoning models have revolutionized the field of computer vision, achieving or even surpassing human-level performances among a collection …

    umn Repository record for Integrating Knowledge Into Visual Reasoning: Enhancing Generalizability, Explainability, And Bias Mitigation (opens in a new tab)

  5. New Approaches to Visual Reasoning in Mathematics and Kantian Characterization of Mathematics

    … is to reveal the true nature of mathematical reasoning and to show the necessity of pictorial representations in mathematics. In order to support my thesis I argue that using only the formal language, without fully integrating visual reasoning in mathematical communication, mathematics …

    fu-berlin Repository record for New Approaches to Visual Reasoning in Mathematics and Kantian Characterization of Mathematics (opens in a new tab)

  6. Association Between Cognition and Depression: A Cross-Sectional and Longitudinal Study of Individuals with Learning Disabilities.

    … how three cognitive processing factors (verbal & visual reasoning, and attention/working memory) were associated with three depressive symptom factors (disturbances in mood, vegetative, and cognitive functioning). The data for SEM came from a large data set of children with learning disabilities …

    unt Repository record for Association Between Cognition and Depression: A Cross-Sectional and Longitudinal Study of Individuals with Learning Disabilities. (opens in a new tab)

  7. A Neuro-Symbolic AI Approach to Scene Understanding in Autonomous Systems

    … representation, representation learning, and reasoning to advance cognitive and visual reasoning in autonomous systems. Our approach involves several key contributions. First, we introduce methods for constructing unified knowledge representations that integrate scene data with background …

    south-carolina Repository record for A Neuro-Symbolic AI Approach to Scene Understanding in Autonomous Systems (opens in a new tab)

  8. Reasoning in visual environments

    Real-world visual tasks require a synchrony of perception and reasoning—people not only perceive the visual environment (e.g. the position of all the objects), but also reason in it. For example, they imagine consequences of actions (e.g. what would happen if I ...), manipulate visual symbols and …

    bu Repository record for Reasoning in visual environments (opens in a new tab)

  9. Solving the Bongard Problems with Language and Code

    … (VLMs) have made great strides in everyday visual tasks, such as captioning a natural image, or answering commonsense questions about such images. But humans possess the puzzling ability to deploy their visualreasoning abilities in radically new situations – a skill rigorously tested by the …

    cornell Repository record for Solving the Bongard Problems with Language and Code (opens in a new tab) Embargoed until 2027-09-09

  10. High-throughput visual knowledge analysis and retrieval in big data ecosystems

    Visual knowledge plays an important role in many highly skilled applications, such as medical diagnosis, geospatial image analysis and pathology diagnosis. Medical practitioners are able to interpret and reason about diagnostic images based on not only primitive-level image features such as color, …

    missouri Repository record for High-throughput visual knowledge analysis and retrieval in big data ecosystems (opens in a new tab)

  11. An investigation of the value of the Peabody picture vocabulary test-revised and the Slosson intelligence test as screening instruments for the fourth edition of the Stanford-Binet intelligence scale

    … except between the PPVT-R and Binet Quantitative Reasoning.Analyses of Variance were used to determine mean differences of scores obtained on the three instruments. Significant differences (p<.05) were found between scores on the PPVT-R and Abstract/Visual Reasoning, SIT and Verbal Reasoning, SIT …

    ballstate-thes Repository record for An investigation of the value of the Peabody picture vocabulary test-revised and the Slosson intelligence test as screening instruments for the fourth edition of the Stanford-Binet intelligence scale (opens in a new tab)

  12. ADVANCING VISION-LANGUAGE PRETRAINING: UNIFIED ARCHITECTURES AND IMPROVED GROUNDING ABILITIES

    The fusion of visual and language pre-training models has significantly advanced AI, particularly in content retrieval, visual reasoning, and multimodal understanding. However, challenges remain in achieving fine-grained semantic alignment and efficient processing of temporal dynamics in video. …

    nus Repository record for ADVANCING VISION-LANGUAGE PRETRAINING: UNIFIED ARCHITECTURES AND IMPROVED GROUNDING ABILITIES (opens in a new tab) Download file for ADVANCING VISION-LANGUAGE PRETRAINING: UNIFIED ARCHITECTURES AND IMPROVED GROUNDING ABILITIES (opens in a new tab)

  13. TOWARDS EFFECTIVE AND EFFICIENT VIDEO UNDERSTANDING

    … addressing domain shifts, semantic grounding, reasoning and attention deficits, and significant computational burdens. Recent advancements in computer vision underscore the need to address these challenges through effective and efficient approaches, which are crucial for applications ranging …

    maryland Repository record for TOWARDS EFFECTIVE AND EFFICIENT VIDEO UNDERSTANDING (opens in a new tab)

  14. Fractal reasoning

    … play a significant role in making sense of the visual world by forming analogies to similar images encountered previously. Yet, while these acts of visual reasoning may be commonplace, the processes of visual analogy are not yet well understood. In this dissertation, I investigate the utility of …

    gatech Repository record for Fractal reasoning (opens in a new tab)

  15. A Unified Token and Parameter Compression Pipeline for High-Resolution Vision–Language Models

    … achieve strong performance on fine-grained visual reasoning tasks, but their deployment remains costly due to large visual token counts and heavy language backbones. This work investigates how to build small and efficient multimodal models while preserving high-resolution reasoning ability. …

    washington Repository record for A Unified Token and Parameter Compression Pipeline for High-Resolution Vision–Language Models (opens in a new tab)

  16. Visual attribute labeling of images

    … analyze and apply various recent techniques in visual attribute recognition and labeling on a common benchmark dataset in order to motivate the design of a novel framework for this task. Using the large scale COCO Attributes dataset as our benchmark, we systematically investigate recent …

    gatech Repository record for Visual attribute labeling of images (opens in a new tab)

  17. Νευροψυχολογική διερεύνηση ασθενών με επιληψία μετωπιαίου λοβού

    … the structure of crystallized intelligence, visual reasoning and new-flanged problem solving, executive functions and metacognitive skills. Moreover, self-administered questionnaires were administered to evaluate the intensity of emotional symptoms. Our results indicated that …

    greece Repository record for Νευροψυχολογική διερεύνηση ασθενών με επιληψία μετωπιαίου λοβού (opens in a new tab)

  18. Lifelong Machine Learning without Lifelong Data Retention

    … image classification and (ii) natural-language visual reasoning. Finally, we extend the idea of continual learning using pre-trained models to the proposed setting of continual customization of text-to-image diffusion models. We hope that our work on enabling models to learn from evolving data …

    gatech Repository record for Lifelong Machine Learning without Lifelong Data Retention (opens in a new tab)

  19. Nova: Privacy-Preserving Goal-Oriented Reasoning in Smart Homes with On-Device Vision-Language Models

    … can operate. Accomplishing such goals requires visual reasoning about the state of the space, coordinated execution across interdependent human and device actions, and sustained multi-turn interaction to progressively transition the environment from an initial state to a desired state. Current …

    vt Repository record for Nova: Privacy-Preserving Goal-Oriented Reasoning in Smart Homes with On-Device Vision-Language Models (opens in a new tab)

  20. Comprehension of humor in children with non-verbal learning disabilites

    … found when the NVLD group was defined as having visual spatial and visual reasoning deficits. However, when the NVLD group was divided into children with and without social perceptual difficulties as defined by the Child and Adolescent Test of Social Perception (CASP), significant group …

    texas Repository record for Comprehension of humor in children with non-verbal learning disabilites (opens in a new tab)

Page 1 of 3