Skip to content
akaturk Academic measurement

OpenAlex topic

Human Pose and Action Recognition

This page lists works and academicians tagged with an OpenAlex topic. It is not a YÖKSİS primary or secondary field.

OpenAlex 1,088 works 46 author topics

Works

1,088 works

  1. OpenAlex top 1% OpenAlex 99.7%

    No abstract yet.

  2. YÖKSİS SJR Q2 JCR Q2 OpenAlex top 1% OpenAlex 99.8%

    Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learnin…

  3. OpenAlex top 1% OpenAlex 99.3%

    No abstract yet.

  4. OpenAlex top 10% OpenAlex 98.6%

    No abstract yet.

  5. OpenAlex top 1% OpenAlex 99.6%

    No abstract yet.

  6. OpenAlex top 1% OpenAlex 99.6%

    Situation awareness is the key to security. Awareness requires information that spans multiple scales of space and time. Smart video surveillance systems are capable of enhancing situational awareness across multiple scales of space and time. However, at the present time, the component technologies are evolving in iso…

  7. OpenAlex top 1% OpenAlex 100.0%

    No abstract yet.

  8. OpenAlex top 1% OpenAlex 99.6%

    No abstract yet.

  9. YÖKSİS SJR Q1 JCR Q1 OpenAlex top 1% OpenAlex 99.6%

    No abstract yet.

  10. YÖKSİS SJR Q1 JCR Q2 OpenAlex top 1% OpenAlex 99.2%

    Sign language recognition is a challenging problem where signs are identified by simultaneous local and global articulations of multiple sources, i.e. hand shape and orientation, hand movements, body posture, and facial expressions. Solving this problem computationally for a large vocabulary of signs in real life sett…

  11. YÖKSİS SJR Q1 JCR Q1 OpenAlex top 10% OpenAlex 98.6%

    We propose a distributed, real-time computing platform for tracking multiple interacting persons in motion. To combat the negative effects of occlusion and articulated motion we use a multiview implementation, where each view is first independently processed on a dedicated processor. This monocular processing uses a p…

  12. We present flattened convolutional neural networks that are designed for fast feedforward execution. The redundancy of the parameters, especially weights of the convolutional filters in convolutional neural networks has been extensively studied and different heuristics have been proposed to construct a low rank basis…

Academicians

46 academicians