Sensitive-Video Analysis
Resumo
Sensitive videos that may be inadequate to some audiences (e.g., pornography and violence, towards underages) are constantly being shared over the Internet. Employing humans for filtering them is daunting. The huge amount of data and the tediousness of the task ask for computer-aided sensitive videoanalysis, which we tackle in two ways. In the first one (sensitive-video classification), we explore efficient methods to decide whether or not a video contains sensitive material. In the second one (sensitive-content localization), we explore manners to find the moments a video starts and ceases to display sensitive content. Hypotheses are stated and validated, leading to contributions (papers, dataset, and patents) in the fields of Digital Forensics and Computer Vision.
Referências
Avila, S., Moreira, D., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., and Rocha, A. (2016a). Método Multimodal e em Tempo Real para Filtragem de Conteúdo Sensível. Patent BR 10 2016 007265 4.
Avila, S., Moreira, D., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., and Rocha, A. (2016b). Multimodal and Real-Time Method for Filtering Sensitive Media. Patent US 15/198,626.
Moreira, D. (2016). [link].
Moreira, D. (2017). [link].
Moreira, D., Avila, S., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., and Rocha, A. (2015). RECOD at MediaEval 2015: Affective Impact of Movies Task. In MediaEval, pages 1–2.
Moreira, D., Avila, S., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., and Rocha, A. (2016). Pornography Classification: The Hidden Clues in Video Space-Time. Elsevier Forensic Science International, 268:46–61.
Moreira, D., Avila, S., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., and Rocha, A. (2017a). Multimodal Data Fusion for Sensitive Scene Localization. Elsevier Information Fusion (under review).
Moreira, D., Avila, S., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., and Rocha, A. (2017b). Temporal Robust Features for Violence Detection. In IEEE WACV, pages 392–399.
