An Attention Model for group-level emotion recognition
This work addresses emotion recognition for groups in images, which is an incremental improvement in computer vision.
The paper tackles group-level emotion recognition in images by combining global image and local face representations using an attention mechanism, achieving 64.83% accuracy on the EmotiW 2018 challenge test set and ranking 4th.
In this paper we propose a new approach for classifying the global emotion of images containing groups of people. To achieve this task, we consider two different and complementary sources of information: i) a global representation of the entire image (ii) a local representation where only faces are considered. While the global representation of the image is learned with a convolutional neural network (CNN), the local representation is obtained by merging face features through an attention mechanism. The two representations are first learned independently with two separate CNN branches and then fused through concatenation in order to obtain the final group-emotion classifier. For our submission to the EmotiW 2018 group-level emotion recognition challenge, we combine several variations of the proposed model into an ensemble, obtaining a final accuracy of 64.83% on the test set and ranking 4th among all challenge participants.