Fight Detection from Still Images in the Wild


Creative Commons License

Aktı Ş., Ofli F., Imran M., Ekenel H. K.

22nd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Hawaii, United States Of America, 4 - 08 January 2022, pp.550-559 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/wacvw54805.2022.00061
  • City: Hawaii
  • Country: United States Of America
  • Page Numbers: pp.550-559
  • Istanbul Technical University Affiliated: Yes

Abstract

Detecting fights from still images shared on social media is an important task required to limit the distribution of violent scenes in order to prevent their negative effects. For this reason, in this study, we address the problem of fight detection from still images collected from the web and social media. We explore how well one can detect fights from just a single still image. We also propose a new dataset, named Social Media Fight Images (SMFI), comprising realworld images of fight actions. Results of the extensive experiments on the proposed dataset show that fight actions can be recognized successfully from still images. That is, even without exploiting the temporal information, it is possible to detect fights with high accuracy by utilizing appearance only. We also perform cross-dataset experiments to evaluate the representation capacity of the collected dataset. These experiments indicate that, as in the other computer vision problems, there exists a dataset bias for the fight recognition problem. Although the methods achieve close to 100% accuracy when trained and tested on the same fight dataset, the cross-dataset accuracies are significantly lower, i.e., around 70% when more representative datasets are used for training. SMFI dataset is found to be one of the two most representative datasets among the utilized five fight datasets.