Active Gesture Recognition Using Learned Visual Attention

NeurIPS 1995 pp. 858-864

/neurips/1995/darrell1995neurips-active/

Abstract

We have developed a foveated gesture recognition system that runs in an unconstrained office environment with an active camera. Us(cid:173) ing vision routines previously implemented for an interactive envi(cid:173) ronment, we determine the spatial location of salient body parts of a user and guide an active camera to obtain images of gestures or expressions. A hidden-state reinforcement learning paradigm is used to implement visual attention. The attention module selects targets to foveate based on the goal of successful recognition, and uses a new multiple-model Q-Iearning formulation. Given a set of target and distractor gestures, our system can learn where to foveate to maximally discriminate a particular gesture.

PDF NeurIPS Semantic Scholar

Cite

Text

Darrell and Pentland. "Active Gesture Recognition Using Learned Visual Attention." Neural Information Processing Systems, 1995.

Markdown

[Darrell and Pentland. "Active Gesture Recognition Using Learned Visual Attention." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/darrell1995neurips-active/)

BibTeX

@inproceedings{darrell1995neurips-active,
  title     = {{Active Gesture Recognition Using Learned Visual Attention}},
  author    = {Darrell, Trevor and Pentland, Alex},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {858-864},
  url       = {https://mlanthology.org/neurips/1995/darrell1995neurips-active/}
}