Global

MAIVRIK

Global has so much to offer that we must request you orient your device to portrait or find a larger screen. You won't be disappointed.

Global

MAIVRIK

  • Home
  • About
  • Main
  • Contact
  • Aeriform in
    Action

    Welcome

    Action Selection

    These actions have been performed in multiple ways to increase the diversity of the dataset, for example, a person sitting on the bench and a person sitting on the ground with crossed legs are both labeled as sitting.

    Dataset Annotations

    The videos in the dataset have been annotated using DarkLabel , an open source tool that allows for the labeling of individual frames within the videos.

    Human Detection

    We selected this particular object detector after evaluating several alternatives, including SSD, YOLOV3, YOLOV3-tiny, and Faster R-CNN.

  • About
    The Paper

    Abstract

    Aeriform in-action is a multiview dataset for recognizing human actions in aerial videos. The proposed dataset consists of 32 high resolution videos containing 13 action classes with 55,477 frames (without augmentation) and 400,000 annotations captured at 30fps and a resolution of 3840 x 2160 pixels. The dataset addresses several concerns like camera motion, illumination changes, diversity in actions, dynamic transitions of actions etc. The action classes can be categorized as atomic actions, human- human interactions and human-object interactions. The 13 actions are carrying, drinking, handshaking, hugging, kicking, lying, punching, reading, running, sitting, standing, walking and waving. This dataset will provide a baseline for recognizing human actions in aerial videos and will encourage the embedding researchers to progress the field.

  • Stills Taken

  • UIET, South Campus, PU, Sector 25, Chandigarh, India

    ouremail@gmail.com +48 12 628 75 60
    • BÄ“hance
    • dribbble
    • Contact Us
  • You want us to do

  • Home
  • About
  • Main
  • Contact