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 6 of 6 for “"Action retrieval"”.

  1. Human action retrieval of 3D mesh sequences

    … to deal with the problem of unsupervised human action retrieval of 3D mesh sequences. In the first method, a set of state-of-the-art static shape descriptors are used to represent the human body in each frame of the sequences and each mesh sequence is considered as an N-dimensional curve, where …

    greece Repository record for Human action retrieval of 3D mesh sequences (opens in a new tab)

  2. Interactive tracking and action retrieval to support human behavior analysis

    … to reliably code a particular behavior/interaction. Also, manual coding typically takes a lot more time than the actual length of the video (e.g. , it can take up to 6 times the actual length of the video to do human-assisted single object tracking. The time intensive nature of this process …

    gatech Repository record for Interactive tracking and action retrieval to support human behavior analysis (opens in a new tab)

  3. Verbs and Me: An Investigation Into Verbs as Labels for Action Recognition in Video Understanding

    This thesis focuses on the task of fine-grained action understanding in videos,<br/>specifically on the tasks of action recognition and action retrieval, with the<br/>aim of bridging the gap between language and vision. Typically, action seg-<br/>ments were labelled with a (small) chosen set of …

    bristol Repository record for Verbs and Me: An Investigation Into Verbs as Labels for Action Recognition in Video Understanding (opens in a new tab) Download PDF for Verbs and Me: An Investigation Into Verbs as Labels for Action Recognition in Video Understanding (opens in a new tab)

  4. Application specific performance measure optimization using deep learning

    In this thesis, we address the action retrieval and the object category segmentation problems by directly optimizing application specific performance measures using deep learning. Most deep learning methods are designed to optimize simple loss functions (e.g., cross-entropy or hamming loss). These …

    manitoba Repository record for Application specific performance measure optimization using deep learning (opens in a new tab)