The objective of facial attribute recognition is to predict a set of labels for each face image. Similar to general multi-label image classification task, facial attribute recognition suffers from several typical problems: discriminative feature learning, handling the correlations among attributes, and imbalanced training data. In this paper, we propose a unified facial attribute recognition solution via feature decoupling and graph convolutional networks (GCN): 1) We utilize the orthonormal regularizer to constrain that each dimension of the general facial representation represents a certain visual pattern. Meanwhile, a learnable matrix is unveiled, which can convert general facial feature into attribute-specific representation through modeling the importance of different visual patterns. 2) To handle the correlations between facial attributes, we build a GCN to capture the label dependencies and map the nodes in the proposed GCN to a set of interdependent attribute classifiers. Besides, we normalize the weights in all classifiers to alleviate the influence of data imbalance. We have conducted extensive experiments on two benchmarks, and both the qualitative and quantitative evaluation results have demonstrated the effectiveness of the proposed method.

The brain generates predictions about visual word forms to support efficient reading. The “interactive account” suggests that the predictions in visual word processing can be strategic or automatic (non-strategic). Strategic predictions are frequently demonstrated in studies that manipulated task demands, however, few studies have investigated automatic predictions. Orthographic knowledge varies greatly among individuals and it offers a unique opportunity in revealing automatic predictions. The present study grouped the participants by level of orthographic knowledge and recorded EEGs in a non-linguistic color matching task. The visual word-selective N170 response was much stronger to pseudo than to real characters in participants with low orthographic knowledge, but not in those with high orthographic knowledge. Previous work on predictive coding has demonstrated that N170 is a good index for prediction errors, i.e., the mismatches between predictions and visual inputs. The present findings provide unambiguous evidence that automatic predictions modulate the early stage of visual word processing.

No abstract

No abstract

No abstract