Multi-Instance Dynamic Ordinal Random Fields for Weakly Supervised Facial Behavior Analysis

作者：Ruiz Adria^*; Rudovic Ognjen; Binefa Xavier; Pantic Maja

来源：IEEE Transactions on Image Processing, 2018, 27(8): 3969-3982.

DOI：10.1109/TIP.2018.2830189

• Mutiple instance learning
• undirected graphical models
• facial behavior analysis
• pain intensity
• action units

We propose a multi-instance-learning (MIL) approach for weakly supervised learning problems, where a training set is formed by bags (sets of feature vectors or instances) and only labels at bag-level are provided. Specifically, we consider the multi-instance dynamic-ordinal-regression (MI-DOR) setting, where the instance labels are naturally represented as ordinal variables and bags are structured as temporal sequences. To this end, we propose MI dynamic ordinal random fields (MI-DORF). In this paper, we treat instance-labels as temporally dependent latent variables in an undirected graphical model. Different MIL assumptions are modelled via newly introduced high-order potentials relating bag and instance-labels within the energy function of the model. We also extend our framework to address the partially observed MI-DOR problem, where a subset of instance labels is also available during training. We show on the tasks of weakly supervised facial action unit and pain intensity estimation, that the proposed framework outperforms alternative learning approaches. Furthermore, we show that MI-DORF can he employed to reduce the data annotation efforts in this context by large-scale.

• 出版日期2018-8
• 单位MIT; INRIA