Adult content detection in videos with convolutional and recurrent neural networks

Wehrmann, Jônatas; Simes, Gabriel S.; Barros, Rodrigo C.; Cavalcante, Victor F.

doi:10.1016/j.neucom.2017.07.012

Cited by 88 publications

(65 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That can be explained by the fact that some pornographic videos have the additional difficulty of having very few shots with pornographic content (typically one or two takes among several dialog shots or cut scenes). 89.5 ± 1 Caetano et al [43] 92.4 ± 1 TRoF [44] 95 ± ** ACORDE-50* [10] 94.8 ± 2 ACORDE-101* [10] 95. We compared our results with the accuracy from the baseline.…”

Section: B Video Pornography Classificationmentioning

confidence: 98%

See 1 more Smart Citation

FASTensor: A tensor framework for spatiotemporal description

Mota¹,

Santos²,

Araújo³

2019

Anais Estendidos Do XXXII Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2019)

View full text Add to dashboard Cite

Spatiotemporal description is a research field with applications in various areas such as video indexing, surveillance, human-computer interfaces, among others. Big Data problems in large databases are now being treated with Deep Learning tools, however we still have room for improvement in spatiotemporal handcraft description. Moreover, we still have problems that involve small data in which data augmentation and other techniques are not valid. The main contribution of this Ph.D. Thesis 1 is the development of a framework for spatiotemporal representation using orientation tensors enabling dimension reduction and invariance. This is a multipurpose framework called Features As Spatiotemporal Tensors (FASTensor). We evaluate this framework in three different applications: Human Action recognition, Video Pornography classification and Cancer Cell classification. The latter one is also a contribution of this work, since we introduce a new dataset called Melanoma Cancer Cell dataset (MCC). It is a small data that cannot be artificially augmented due the difficulty of extraction and the nature of motion. The results were competitive, while also being fast and simple to implement. Finally, our results in the MCC dataset can be used in other cancer cell treatment analysis.

show abstract

Section: B Video Pornography Classificationmentioning

confidence: 98%

“…Deep Learning-based approaches share similar procedures: patch sampling, feature description/learning and classification [8]. Nowadays, image and video classification problems in large databases are being treated with Deep Learning tools [9], [10].…”

Section: Introductionmentioning

confidence: 99%

FASTensor: A tensor framework for spatiotemporal description

Mota¹,

Santos²,

Araújo³

2019

Anais Estendidos Do XXXII Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2019)

View full text Add to dashboard Cite

show abstract

“…To date, many models are proposed to handle various types of data, such as videos, images [70], and documents in many tasks, for example, object detection [2], content detection [71], data management [73,78], and representation learning for words, sentences and documents [33,38,46,53]. The methodologies of representation learning for documents mainly include undirected graphical models or directed graphical models.…”

Section: Related Workmentioning

confidence: 99%

Bi-Directional Recurrent Attentional Topic Model

Pan

2020

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

In a document, the topic distribution of a sentence depends on both the topics of its neighbored sentences and its own content, and it is usually affected by the topics of the neighbored sentences with different weights. The neighbored sentences of a sentence include the preceding sentences and the subsequent sentences. Meanwhile, it is natural that a document can be treated as a sequence of sentences. Most existing works for Bayesian document modeling do not take these points into consideration. To fill this gap, we propose a bi-Directional Recurrent Attentional Topic Model (bi-RATM) for document embedding. The bi-RATM not only takes advantage of the sequential orders among sentences but also uses the attention mechanism to model the relations among successive sentences. To support to the bi-RATM, we propose a bi-Directional Recurrent Attentional Bayesian Process (bi-RABP) to handle the sequences. Based on the bi-RABP, bi-RATM fully utilizes the bidirectional sequential information of the sentences in a document. Online bi-RATM is proposed to handle large-scale corpus. Experiments on two corpora show that the proposed model outperforms state-of-the-art methods on document modeling and classification.

show abstract

“…Adult video detection [20][21][22][23][24][25][26][27][28][29] can be reckoned as a particular kind of video event detection [13][14][15][16][17][18][19]. It is closely related to adult image detection [33][34][35][36][37][38][39][40][41][42][43][44], salient object detection [1][2][3][4][5][6][7][8][9][10][11][12], and audio content analysis [30][31][32].…”

Section: Related Workmentioning

confidence: 99%

Analyzing periodicity and saliency for adult video detection

Liu

Huang

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

Content-based adult video detection plays an important role in preventing pornography.However, existing methods usually rely on single modality and seldom focus on multi-modality semantics representation. Addressing at this problem, we put forward an approach of analyzing periodicity and saliency for adult video detection. At first, periodic patterns and salient regions are respectively analyzed in audio-frames and visual-frames. Next, the multi-modal co-occurrence semantics is described by combining audio periodicity with visual saliency. Moreover, the performance of our approach is evaluated step by step. Experimental results show that our approach obviously outperforms some state-of-the-art methods.

show abstract

Adult content detection in videos with convolutional and recurrent neural networks

Cited by 88 publications

References 8 publications

FASTensor: A tensor framework for spatiotemporal description

FASTensor: A tensor framework for spatiotemporal description

Bi-Directional Recurrent Attentional Topic Model

Analyzing periodicity and saliency for adult video detection

Contact Info

Product

Resources

About