|Title||Multi-instance Dynamic Ordinal Random Fields for weakly-supervised pain intensity estimation|
|Publication Type||Conference Proceedings|
|Year of Conference||2016|
|Authors||Ruiz, A, Rudovic, O, binefa, X, Pantic, M|
|Conference Name||Asian Conference on Computer Vision (ACCV)|
In this paper, we address the Multi-Instance-Learning (MIL) problem when bag labels are naturally represented as ordinal variables (Multi--Instance--Ordinal Regression). Moreover, we consider the case where bags are temporal sequences of ordinal instances. To model this, we propose the novel Multi-Instance Dynamic Ordinal Random Fields (MI-DORF). In this model, we treat instance-labels inside the bag as latent ordinal states. The Multi-Instance-Learning assumption is modelled by incorporating into the energy function a high-order cardinality potential relating bag and instance-labels. We show the benefits of the proposed approach on the task of weakly-supervised pain intensity estimation from the UNBC Shoulder-Pain Database. Our experiments show that the proposed approach significantly outperforms alternative non-ordinal methods that either ignore the MIL assumption, or do not model dynamic information in target data.