Facial Descriptors for Human Interaction Recognition In Still Images
This addresses a rarely studied area in computer vision for applications like social behavior analysis, but it is incremental as it builds on existing feature extraction and learning methods.
The paper tackles the problem of recognizing human interactions in still images by exploring whether facial regions and their spatial configurations contribute to recognition, and it shows that faces and scene characteristics contain important information for this task.
This paper presents a novel approach in a rarely studied area of computer vision: Human interaction recognition in still images. We explore whether the facial regions and their spatial configurations contribute to the recognition of interactions. In this respect, our method involves extraction of several visual features from the facial regions, as well as incorporation of scene characteristics and deep features to the recognition. Extracted multiple features are utilized within a discriminative learning framework for recognizing interactions between people. Our designed facial descriptors are based on the observation that relative positions, size and locations of the faces are likely to be important for characterizing human interactions. Since there is no available dataset in this relatively new domain, a comprehensive new dataset which includes several images of human interactions is collected. Our experimental results show that faces and scene characteristics contain important information to recognize interactions between people.