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 “"View-invariant"”.

  1. Pattern codes for perceived gaze direction revealed by functional MRI

    … of social cues, including gaze direction, head view, and body posture. Furthermore, a subset of such neurons respond to a single direction across multiple cues, suggesting that the code is driven by the direction of another's social attention regardless of how this is conveyed. Attempts to …

    cambridge Repository record for Pattern codes for perceived gaze direction revealed by functional MRI (opens in a new tab)

  2. High-level visual object representation in juvenile and adult primates

    Despite being reflexive, primate view invariant object recognition is a complex computational task. These computations are thought to reside in the ventral visual stream, specifically culminating in inferior temporal (IT) cortex. Recent research in machine learning has made great progress in …

    mit Repository record for High-level visual object representation in juvenile and adult primates (opens in a new tab)

  3. Object Tracking And Activity Recognition In Video Acquired Using Mobile Cameras

    … the “action sketch”. An action sketch is a view invariant representation obtained by analyzing important changes that occur during the motion of the objects. When an actor performs an action in 3D, the points on the actor generate space-time trajectories in four dimensions (x, y, z,t). …

    ucf

  4. Human detection and action recognition using depth information by Kinect

    … from Kinect, our method demonstrates significant view invariance on our 3D action dataset. Our dataset is composed of 200 3D sequences of 10 indoor activities performed by 10 individuals in varied views. Our method is real-time and achieves superior results on the challenging 3D action dataset. We …

    texas Repository record for Human detection and action recognition using depth information by Kinect (opens in a new tab)

  5. Algorithms for Gait-Based Human Identification from a Monocular Video Sequence

    … rely on the availability of an exact side view in the probe. However, it is not realistic to expect that this assumption will be valid in most real-life scenarios. We present a view invariant gait recognition algorithm which is based on synthesizing a side view of a person from an arbitrary …

    maryland Repository record for Algorithms for Gait-Based Human Identification from a Monocular Video Sequence (opens in a new tab)