Anti-Sequences: Event Detection by Frame Stacking

Abstract

This paper presents a nattiral extension of the new4 introdticed “anti-face ” method to event detection, both in the image and in the feattire domains. In the caJe of the image domain (video segtience $ we create spatio-temporal templates by stacking the video framw, and the detection is pe formed on these templates. In order to recogzixe the motion of feattires in a video segtience, the spatial locations of the feattires are modtilated in time, tLxzw creating a one-dimensional vector which represents the event. The followifzg appl zca t ions of anti-sequences are presented: 7) Detection of an oeect tinder 3D rotations in a video segtience simtizated from the CO IL da.tabaJe, 2) VistiaZ speech recognition of spoken word; poifzter. and 3) Recognition of JJE&OZJ sketched with a laser The restiZtizg detection algorhhz is vey fast, and is rebut enotigh to work on small &wags. AZJO, it is capable of dim&hating the desired event-template from a&ray events, and not OE+ events in a ‘hegative traikg set’: 1.

Cite

Text

Osadchy et al. "Anti-Sequences: Event Detection by Frame Stacking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990923

Markdown

[Osadchy et al. "Anti-Sequences: Event Detection by Frame Stacking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/osadchy2001cvpr-anti/) doi:10.1109/CVPR.2001.990923

BibTeX

@inproceedings{osadchy2001cvpr-anti,
  title     = {{Anti-Sequences: Event Detection by Frame Stacking}},
  author    = {Osadchy, Margarita and Keren, Daniel and Gal, Yaniv},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:46-51},
  doi       = {10.1109/CVPR.2001.990923},
  url       = {https://mlanthology.org/cvpr/2001/osadchy2001cvpr-anti/}
}