A Survey on Web Multimedia Mining

Kamde, Pravin M.; Algur, Siddu P.

doi:10.5121/ijma.2011.3307

Cited by 11 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, it is worth highlighting NLTK (Natural Language Toolkit) from the Python community. In the arena of multimedia, facilities and prototypes for emotion recognition, human age estimation based on facial information, motion intensity, energy measures, colour histograms, dominant colour, colour A report into mining multimedia observed: 'An interesting research direction on web content mining is the integration of heterogeneous information sources' (Kamde and Algur, 2011). This concurs with the emphasis placed in forensics on multiple sources of evidence.…”

Section: Text and Multimedia Miningmentioning

confidence: 78%

Digital Forensics and Preservation

John¹

2012

View full text Add to dashboard Cite

The Digital Preservation Coalition (DPC) is an advocate and catalyst for digital preservation, ensuring our members can deliver resilient long-term access to digital content and services. It is a not-forprofit membership organization whose primary objective is to raise awareness of the importance of the preservation of digital material and the attendant strategic, cultural and technological issues. It supports its members through knowledge exchange, capacity building, assurance, advocacy and partnership. The DPC's vision is to make our digital memory accessible tomorrow. The DPC Technology Watch Reports identify, delineate, monitor and address topics that have a major bearing on ensuring our collected digital memory will be available tomorrow. They provide an advanced introduction in order to support those charged with ensuring a robust digital memory, and they are of general interest to a wide and international audience with interests in computing, information management, collections management and technology. The reports are commissioned after consultation among DPC members about shared priorities and challenges; they are commissioned from experts; and they are thoroughly scrutinized by peers before being released. The authors are asked to provide reports that are informed, current, concise and balanced; that lower the barriers to participation in digital preservation; and that they are of wide utility. The reports are a distinctive and lasting contribution to the dissemination of good practice in digital preservation. This report was written by Jeremy Leighton John, a specialist in the theory and practice of digital forensics in the context of personal, cultural and scientific archives. The report is published by the DPC in association with Charles Beagrie Ltd. Neil Beagrie, Director of Consultancy at Charles Beagrie Ltd, was commissioned to act as principal investigator for, and managing editor of this Series in 2011. He has been further supported by an Editorial Board drawn from DPC members and peer reviewers who comment on text prior to release:

show abstract

Section: Text and Multimedia Miningmentioning

confidence: 78%

Digital Forensics and Preservation

John¹

2012

View full text Add to dashboard Cite

show abstract

“…In this paper, a 500ms segment length and 32ms frame length with a 50% overlap are used. Second, MFCCs are computed in each frame, and the q-th MFCC of the t-th frame of k-th segment, C k,t (q), is calculated as (1), where E k,t (b) is the energy of the b-th mel-scaled bandpass filter of the t-th frame of the k-th segment, q is the quefrency index, and B is the number of mel-scale bandpass filters.…”

Section: Repeated Curve-like Spectrum Featurementioning

confidence: 99%

“…The rapid development of multimedia technologies and advances in internet infrastructure have allowed general users to easily create, edit, and post their own content, and it is even easier to access any Internet content if so desired [1]. However, this has also led to a harmful side effect, which is the creation and distribution of uncontrolled X-rated videos.…”

Section: Introductionmentioning

confidence: 99%

Untitled

2011

IJMA

View full text Add to dashboard Cite

This paper addresses the automatic classification of X-rated videos by analyzing its obscene sounds. In this paper, obscene sounds refer to audio signals generated from sexual moans and screams during sexual scenes. By analyzing various sound samples, we determined the distinguishable characteristics of obscene sounds and propose a repeated curve-like spectrum feature that represents the characteristics of such sounds. We constructed 6,269 audio clips to evaluate the proposed feature, and separately constructed 1,200 X-rated and general videos for classification. The proposed feature has an F1-score, precision, and recall rate of 96.6%, 98.2%, and 95.2%, respectively, for the original dataset, and 92.6%, 97.6%, and 88.0% for a noisy dataset of 5dB SNR. And, in classifying videos, the feature has more than a 90% F1-score, 97% precision, and an 84% recall rate. From the measured performance, X-rated videos can be classified with only the audio features and the repeated curve-like spectrum feature is suitable to detect obscene sounds.

show abstract

Constructing a Novel Pos-neg Manifold for Global-Based Image Classification

Zhu

Yang

et al. 2013

Advanced Data Mining and Applications

View full text Add to dashboard Cite

A Survey on Web Multimedia Mining

Cited by 11 publications

References 39 publications

Digital Forensics and Preservation

Digital Forensics and Preservation

Untitled

Constructing a Novel Pos-neg Manifold for Global-Based Image Classification

Contact Info

Product

Resources

About