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 14 of 14 for “"Cross-Modal Learning"”.

  1. Self-supervised and cross-modal learning from videos

    <p>Deep learning has demonstrated impressive results for tasks where the training of neural networks can be supervised with paired input and manually labelled output data. However, labelling data can be expensive and might not be feasible for some applications. In this thesis, we consider learning …

    oxford Repository record for Self-supervised and cross-modal learning from videos (opens in a new tab)

  2. Cross-modal learning from visual information for activity recognition on inertial sensors

    … and variation in recorded environments. Machine learning models, developed using these small datasets, are effectively blind to the diverse expressions of activities performed by wide-ranging populations in the real world, and progress in wearable inertial sensing is held back by this bottleneck …

    oxford Repository record for Cross-modal learning from visual information for activity recognition on inertial sensors (opens in a new tab)

  3. SELF SUPERVISED LEARNING FOR ACCURATE BIOMARKER PREDICTION

    Recent advances in self-supervised learning (SSL) have opened up new possibilities for accurate biomarker prediction, particularly in the scenario where labeled medical data is scarce. This thesis explores the use of SSL approaches to electrocardiogram (ECG) signal representation learning, a common …

    nus Repository record for SELF SUPERVISED LEARNING FOR ACCURATE BIOMARKER PREDICTION (opens in a new tab) Download file for SELF SUPERVISED LEARNING FOR ACCURATE BIOMARKER PREDICTION (opens in a new tab)

  4. Bridging Domain Gaps for Cross-Spectrum and Long-range Face Recognition Using Domain Adaptive Machine Learning

    … when presented with images fromdifferent modalities or domains( such as infrared to visible, long range to close range,nighttime to daytime, profile to f rontal, e tc.) Additionally, advancements in camerasensors, analytics beyond the visible spectrum, and the increasing size of …

    nebraska Repository record for Bridging Domain Gaps for Cross-Spectrum and Long-range Face Recognition Using Domain Adaptive Machine Learning (opens in a new tab)

  5. Connecting vision and language via image retrieval and captioning

    … and language, e.g. image/video captioning, multi-modal image retrieval, visual question answering. In this thesis, we consider several problems in cross-modal learning from vision and language. First, the problem of composed query image retrieval is studied. In this problem, the objective is to …

    manitoba Repository record for Connecting vision and language via image retrieval and captioning (opens in a new tab)

  6. Augmenting Video Retrieval: Leveraging Auxiliary Information to Enhance Retrieval Tasks

    … understanding, focusing on the task of cross-modal video retrieval and the challenge of bridging the gap between video and text modalities.<br/>Traditional retrieval methods often rely on a textual query (e.g., video caption) or a<br/>visual query (e.g., video clip) to retrieve the …

    bristol Repository record for Augmenting Video Retrieval: Leveraging Auxiliary Information to Enhance Retrieval Tasks (opens in a new tab) Download PDF for Augmenting Video Retrieval: Leveraging Auxiliary Information to Enhance Retrieval Tasks (opens in a new tab)

  7. Data-Efficient Machine Learning Methods in Healthcare Applications

    Machine learning (ML) offers transformative potential in healthcare, but its application is frequently constrained by data efficiency challenges, including the difficulty of acquiring large labeled datasets, privacy regulations limiting data sharing, and the burden of extensive multi-modal data …

    gatech Repository record for Data-Efficient Machine Learning Methods in Healthcare Applications (opens in a new tab)

  8. Robust multi-modal imaging in the presence of incomplete modalities

    … and type of channels can vary drastically across domains such as microscopy and remote sensing. Existing neural networks are typically fixed-channel, limiting their reusability in settings where channel configurations change. To address this, we introduced the first systematic benchmark for …

    bu Repository record for Robust multi-modal imaging in the presence of incomplete modalities (opens in a new tab)

  9. Interactive shared visuo-tactile perception and learning in robotics

    … approaches for visuo-tactile perception and learning in robotics, focussing on object pose estimation, recognition, and reconstruction. For robust pose estimation of unknown objects in dense clutter, a novel recursive filtering formulation termed translation-invariant Quaternion filter (TIQF) …

    glasgow Repository record for Interactive shared visuo-tactile perception and learning in robotics (opens in a new tab) Download PDF for Interactive shared visuo-tactile perception and learning in robotics (opens in a new tab)

  10. Operationalizing Physics-Informed Deep Learning in Fire Safety: A Robust Design and Product Lifecycle Approach

    … develops VisionKoopmanNet, an image-based deep learning pipeline that estimates HRR directly from optical video and embeds these predictions within a structured operational framework for safety-critical evaluation. The technical pipeline is built in three phases. Phase 1 trains a …

    chalmers Repository record for Operationalizing Physics-Informed Deep Learning in Fire Safety: A Robust Design and Product Lifecycle Approach (opens in a new tab)

  11. A survey of IMU based cross-modal transfer learning in human activity recognition

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01

    uiuc Repository record for A survey of IMU based cross-modal transfer learning in human activity recognition (opens in a new tab)

  12. Audio Processing in the Age of Large Language Models

    … processing research has lagged behind other modalities like language and vision. This disparity is due to several factors, including the scarcity of large-scale datasets, advanced architectures, and the need for more effective training methods to address the inherent complexities of audio …

    maryland Repository record for Audio Processing in the Age of Large Language Models (opens in a new tab)

  13. Multimodal Representation Learning for Face Understanding: From Caption Supervision to Foundation Model Adaptation

    … have greatly improved visual representation learning, their patch-based tokenization and lack of spatial inductive bias limit their ability to capture fine-grained details in low-resolution inputs. This dissertation investigates multimodal representation learning for face understanding …

    wvu Repository record for Multimodal Representation Learning for Face Understanding: From Caption Supervision to Foundation Model Adaptation (opens in a new tab)

  14. Integrating natural language with molecular structure

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms

    uiuc Repository record for Integrating natural language with molecular structure (opens in a new tab)