Action Recognition in Still Images With Minimum Annotation Efforts

Published date : 01 Sep 2016

We focus on the problem of still image-based human action recognition, which essentially involves making prediction by analyzing human poses and their interaction with objects in the scene. Besides image-level action labels (e.g., riding, phoning), during both training and testing stages, existing works usually require additional input of human bounding boxes to facilitate the characterization of the underlying human–object interactions. We argue that this additional input requirement might severely discourage potential applications and is not very necessary. To this end, a systematic approach was developed in this paper to address this challenging problem of minimum annotation efforts, i.e., to perform recognition in the presence of only image-level action labels in the training stage. Experimental results on three benchmark data sets demonstrate that compared with the state-of-the-art methods that have privileged access to additional human bounding-box annotations, our approach achieves comparable or even superior recognition accuracy using only action annotations in training. Interestingly, as a by-product in many cases, our approach is able to segment out the precise regions of underlying human–object interactions.

type
Journal Paper
journal
IEEE Transactions on Image Processing, Vol. 25, Issue 11, Nov 2016, Pg 5479-5490, doi: 10.1109/TIP.2016.2605305
Url
http://ieeexplore.ieee.org/document/7558119/
Impact Factor
3.735