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 5 of 5 for “"Motion Consistency"”.
-
Filter Design and Consistency Evaluation for 3D Tongue Motion Estimation using Harmonic Phase Analysis Method
Understanding patterns of tongue motion in speech using 3D motion estimation is challenging. Harmonic phase analysis has been used to perform noninvasive tongue motion and strain estimation using tagged magnetic resonance imaging (MRI). Two main contributions have been made in this thesis. First, …
-
Static and dynamic performance during precision fine motor tracking
… to examine possible differences in accuracy or consistency of performance between static and dynamic variations of a precision fine motor tracking task. Nineteen healthy, right-handed volunteer participants were asked to manipulate a cursor to track a moving target with both index fingers, using …
-
Diffusion models for visual content generation : challenges and insights
… this research gap, we propose the Fréchet Video Motion Distance (FVMD) metric, which focuses on evaluating motion consistency in video generation. Specifically, we design explicit motion features based on key-point tracking and then measure the similarity between these features via the Fréchet …
-
ROBUST TECHNIQUES FOR VISUAL SURVEILLANCE
… Third, we present a tracking algorithm based on motion analysis of regional affine invariant image features. The tracked object is represented with a probabilistic occupancy map. Using this map as support, regional features are detected and matched across frames. The motion of pixels is then …
-
Evaluating Multimodal AI Systems: A Comparative Analysis of Large Languagel Model-Based Models for Text, Image, and Video Generation
… video content creation, text-to-image-to-text consistency, and automatic text summarization. The first study investigates the potential of AI-powered text-to-video generation to democratize video production and enhance storytelling. By comparing the performance of three models—ModelScope, …