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 7 of 7 for “"Video alignment"”.

  1. Video alignment to a common reference

    Handheld videos often include unintentional motion (jitter) and intentional motion (pan and/or zoom). Human viewers prefer to see jitter removed, creating a smoothly moving camera. For video analysis, in contrast, aligning to a fixed stable background is sometimes preferable. This paper presents an …

    colostate Repository record for Video alignment to a common reference (opens in a new tab)

  2. Probabilistic Temporal Correspondence Learning for Self-Supervised Video Alignment

    Video alignment, the task of establishing temporal correspondences between frames of videos that depict the same activity, is a fundamental building block for applications ranging from action recognition to rehabilitation monitoring and robotic imitation learning. Self-supervised methods based on …

    unt Repository record for Probabilistic Temporal Correspondence Learning for Self-Supervised Video Alignment (opens in a new tab)

  3. Selected topics in video coding and computer vision

    Video applications ranging from multimedia communication to computer vision have been extensively studied in the past decades. However, the emergence of new applications continues to raise questions that are only partially answered by existing techniques. This thesis studies three selected topics …

    wvu Repository record for Selected topics in video coding and computer vision (opens in a new tab)

  4. Task Progress Assessment and Monitoring Using Self-Supervised Learning

    … frame-level state representation with ”temporal video alignment” and ”contrastive learning.”In this work, we use self-supervised learning to train a model using multiple videos of the same action being performed in various settings. This model can extract frame-level embedding space and align …

    usf Repository record for Task Progress Assessment and Monitoring Using Self-Supervised Learning (opens in a new tab)

  5. Deep Neural Network Design for Video Understanding

    This thesis focuses on enhancing video understanding through innovative deep neural network designs, tackling the primary challenges in video analysis tasks. It addresses the critical aspects of handling high dimensionality and data volume, interpreting temporal dynamics and sequential …

    unsw Repository record for Deep Neural Network Design for Video Understanding (opens in a new tab)

  6. Skeleton-Based Human Activity Recognition using Temporal Cycle-Consistency Learning

    … skeleton data is an effective compression of video data for activity recognition. There has been only limited research into the application of few-shot techniques, where clips are compared to samples from a subset of classes, using skeleton activity data. Additionally, temporal alignment …

    queens Repository record for Skeleton-Based Human Activity Recognition using Temporal Cycle-Consistency Learning (opens in a new tab)

  7. Automatic Content-Based Temporal Alignment of Image Sequences with Varying Spatio-Temporal Resolution

    … to time. This limits the generality of such alignment solutions. We present an unsupervised method that utilizes a content-based clustering mechanism in order to temporally align multiple non-synchronized image sequences of different and varying spatio-temporal resolutions. We show that the …

    byu Repository record for Automatic Content-Based Temporal Alignment of Image Sequences with Varying Spatio-Temporal Resolution (opens in a new tab) Download PDF for Automatic Content-Based Temporal Alignment of Image Sequences with Varying Spatio-Temporal Resolution (opens in a new tab)