Happy to share the latest result of our #ArtificialIntelligence research group. How to detect violence in videos? Work in partnership with Bruno Malveira Peixoto , Bahram Lavi , and Zanoni Dias appearing at the Elsevier Journal of Visual Communication and Image Representation (JVCI). 😍😊
[FREE ACCESS] https://lnkd.in/e4r8Zk6
Violence is one of the hardest concepts to define objectively. We propose a method that aims to enable machines to understand a high-level concept of violence by first breaking it down into smaller, more objective ones, such as fights, explosions, blood, and gunshots. We leverage characteristics of each individual sub-concept of violence (relying upon custom-tailored convolutional neural networks) to guide how they should be described.
This robust and modular approach allows different cultures and users to adapt the detector to their specific needs.