Daniel de Carvalho Moreira

Video pornography detection through deep learning techniques and motion information

Recent literature has explored automated pornographic detection - a bold move to replace humans in the tedious task of moderating online content. Unfortunately, on scenes with high skin exposure, such as people sunbathing and wrestling, the state of the art can have many false alarms. This paper is based on the premise that incorporating motion information in the models can alleviate the problem of mapping skin exposure to pornographic content, and advances the bar on automated pornography detection with the use of motion information and deep learning architectures. Deep Learning, especially in the form of Convolutional Neural Networks, have striking results on computer vision, but their potential for pornography detection is yet to be fully explored through the use of motion information. We propose novel ways for combining static (picture) and dynamic (motion) information using optical flow and MPEG motion vectors. We show that both methods provide equivalent accuracies, but that MPEG motion vectors allow a more efficient implementation. The best proposed method yields a classification accuracy of 97.9% - an error reduction of 64.4% when compared to the state of the art - on a dataset of 800 challenging test cases. Finally, we present and discuss results on a larger, and more challenging, dataset.

Pornography classification: The hidden clues in video space-time.

As web technologies and social networks become part of the general publics life, the problem of automatically detecting pornography is into every parents mind - nobody feels completely safe when their children go online. In this paper, we focus on video-pornography classification, a hard problem in which traditional methods often employ still-image techniques - labeling frames individually prior to a global decision. Frame-based approaches, however, ignore significant cogent information brought by motion. Here, we introduce a space-temporal interest point detector and descriptor called Temporal Robust Features (TRoF). TRoF was custom-tailored for efficient (low processing time and memory footprint) and effective (high classification accuracy and low false negative rate) motion description, particularly suited to the task at hand. We aggregate local information extracted by TRoF into a mid-level representation using Fisher Vectors, the state-of-the-art model of Bags of Visual Words (BoVW). We evaluate our original strategy, contrasting it both to commercial pornography detection solutions, and to BoVW solutions based upon other space-temporal features from the scientific literature. The performance is assessed using the Pornography-2k dataset, a new challenging pornographic benchmark, comprising 2000 web videos and 140h of video footage. The dataset is also a contribution of this work and is very assorted, including both professional and amateur content, and it depicts several genres of pornography, from cartoon to live action, with diverse behavior and ethnicity. The best approach, based on a dense application of TRoF, yields a classification error reduction of almost 79% when compared to the best commercial classifier. A sparse description relying on TRoF detector is also noteworthy, for yielding a classification error reduction of over 69%, with 19× less memory footprint than the dense solution, and yet can also be implemented to meet real-time requirements.

Temporal Robust Features for Violence Detection

Automatically detecting violence in videos is paramount for enforcing the law and providing the society with better policies for safer public places. In addition, it may be essential for protecting minors from accessing inappropriate contents on-line, and for helping parents choose suitable movie titles for their children. However, this is an open problem as the very definition of violence is subjective and may vary from one society to another. Detecting such nuances from video footages with no human supervision is very challenging. Clearly, when designing a computer-aided solution to this problem, we need to think of efficient (quickly harness large troves of data) and effective detection methods (robustly filter what needs special attention and further analysis). In this vein, we explore a content description method for violence detection founded upon temporal robust features that quickly grasp video sequences, automatically classifying violent videos. The used method also holds promise for fast and effective classification of other recognition tasks (e.g., pornography and other inappropriate material). When compared to more complex counterparts for violence detection, the method shows similar classification quality while being several times more efficient in terms of runtime and memory footprint.

A critical analysis of research of a mass-housing programme

ABSTRACT A recent expansion of mass-housing programmes has occurred in emerging economies. The analysis of research on programmes raises questions about what type of research is produced and what its impact is on housing. The Brazilian ‘My House, My Life’ (Minha Casa, Minha Vida – MCMV) programme demonstrates that more of the same type of housing is produced and that the focus of most research repeats the same mistakes. Three million homes have been built and the research community has examined the programme’s social, economic and environmental impacts. A total of 2477 scientific studies on MCMV are analyzed. Few studies were found to assess living conditions from a user perspective at the residential unit scale. Although improvements have occurred on some social issues, the siting of housing on the urban periphery is problematic for urban mobility, social segregation and aesthetic monotony. Also, the design model does not respond to the diverse needs of inhabitants. Opportunities are identified for actions and essential missing research on mass housing. Retrofit strategies are urgent and social cost studies should induce change to the design model. Evidence-based research is needed to support policies and design processes for affordable and quality housing solutions that value users, their needs and aspirations.