Gaze-based Visual Feature Extraction via DLPCCA for Visual Sentiment Estimation

摘要

This paper presents gaze-based visual feature extraction via Discriminative Locality Preserving Canonical Corre-lation Analysis (DLPCCA) for visual sentiment estimation. The proposed method calculates novel visual featuresreecting users' visual sentiment by applying DLPCCA to gaze and original visual features. Consequently, accu-rate visual sentiment estimation becomes feasible by utilizing the novel visual features derived by the proposedmethod.