Structure Inference Machines: Recurrent Neural Networks for Analyzing
Relations in Group Activity Recognition
release_exnlbwkkgrh3pj2eyg5i7jxu2i
by
Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori
2015
Abstract
Rich semantic relations are important in a variety of visual recognition
problems. As a concrete example, group activity recognition involves the
interactions and relative spatial relations of a set of people in a scene.
State of the art recognition methods center on deep learning approaches for
training highly effective, complex classifiers for interpreting images.
However, bridging the relatively low-level concepts output by these methods to
interpret higher-level compositional scenes remains a challenge. Graphical
models are a standard tool for this task. In this paper, we propose a method to
integrate graphical models and deep neural networks into a joint framework.
Instead of using a traditional inference method, we use a sequential inference
modeled by a recurrent neural network. Beyond this, the appropriate structure
for inference can be learned by imposing gates on edges between nodes.
Empirical results on group activity recognition demonstrate the potential of
this model to handle highly structured learning tasks.
In text/plain
format
Archived Files and Locations
application/pdf 710.5 kB
file_gtp636e3xnhk5bc7bcwfvtwq5q
|
arxiv.org (repository) web.archive.org (webarchive) |
1511.04196v1
access all versions, variants, and formats of this works (eg, pre-prints)