| Full text | |
| Author(s): |
Total Authors: 4
|
| Affiliation: | [1] Univ Estadual Campinas, Inst Comp, BR-13083852 Campinas, SP - Brazil
Total Affiliations: 1
|
| Document type: | Journal article |
| Source: | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION; v. 78, JUL 2021. |
| Web of Science Citations: | 0 |
| Abstract | |
In detecting sensitive media, violence is one of the hardest to define objectively, and thus, a significant challenge to detect automatically. While many studies were conducted in detecting aspects of violence, very few try to approach the general concept. 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, to combine them later, leading to a better understanding of the scene. For this, we leverage characteristics of each individual sub-concept of violence (relying upon custom-tailored convolutional neural networks) to guide how they should be described. A fight scene should incorporate temporal features that a scene with blood does not need to describe. A scene with explosions or gunshots should weigh more on its audio features. With this multimodal approach, we trained visual and auditory feature detectors and later combined them into a decision neural network to give us a violence detector that considers several different aspects of the problem. This robust and modular approach allows different cultures and users to adapt the detector to their specific needs. (AU) | |
| FAPESP's process: | 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events |
| Grantee: | Anderson de Rezende Rocha |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 18/05668-3 - Feature-space-time Coherence with Heterogeneous Data |
| Grantee: | Bahram Lavi Sefidgari |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |