Visual Interest Prediction with Attentive Multi-Task Transfer Learning
This addresses the problem of predicting emotional responses to images for applications in photography, advertising, or content recommendation, though it appears incremental as it builds on existing techniques.
The paper tackles visual interest and affect prediction in digital photos by proposing a neural network model combining transfer learning, attention mechanisms, and multi-task learning, achieving large improvements over state-of-the-art systems on a benchmark dataset.
Visual interest & affect prediction is a very interesting area of research in the area of computer vision. In this paper, we propose a transfer learning and attention mechanism based neural network model to predict visual interest & affective dimensions in digital photos. Learning the multi-dimensional affects is addressed through a multi-task learning framework. With various experiments we show the effectiveness of the proposed approach. Evaluation of our model on the benchmark dataset shows large improvement over current state-of-the-art systems.