Short user-generated videos classification using accompanied audio categories

Guo, Jinlin; Gurrin, Cathal

doi:10.1145/2390214.2390220

Cited by 9 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of the video classification work attempts to classify an entire video clip into one of several genres, such as sports, news, cartoon, music. In general, the previous methods can be categorized into four types: text-based approaches [1,23], audio feature based approaches [5,15,17], visual feature based approaches [4,20,22], and those that used some combination of text, audio and visual features [3,4,8]. In fact, most authors incorporated audio and visual features into their approaches (we call it content-based approaches), and these approaches achieved good performance.…”

Section: Related Workmentioning

confidence: 99%

“…Ways of using these features investigated in existed work include many of the standard classifiers because of their ubiquitous nature, such as KNN [8,22], Linear Discriminant Analysis (LDA) [8], SVM [3,4,5,8,16,21], C4.5 decision tree [4,9], GMM [11,12,17,20]. Moreover, some more complicated methods such as HMM [4,19,20] and neural networks [12] were also introduced to video genre classification.…”

Section: Related Workmentioning

confidence: 99%

“…In previous work, MFCC features directly or their statistics such as mean and standard deviation were used for video classification [3,15]. In this work, we will use MFCC together with the bag-of-audioword (BoAW) representation following the method in [5].…”

Section: Audio Featurementioning

confidence: 99%

See 2 more Smart Citations

Who produced this video, amateur or professional?

Guo

Gurrin

Lao³

2013

Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval

Self Cite

View full text Add to dashboard Cite

As the increasing affordability for capturing and storing video and the proliferation of Web 2.0 applications, video content is no longer necessarily created and supplied by a limited number of professional producers; any amateur can produce and publish his/her video quickly. Therefore, the amount of both professional-produced as well as amateur-produced video on the web is ever increasing. In this work, we propose a question; whether we can automatically classify an Internet video clip as being either professional-produced or amateur-produced? Hence, we investigate features and classification methods to answer this question. Based on the differences in the production processes of these two video categories, four features including camera motion, structure, audio feature and combined feature are adopted and studied along with with four popular classifiers KNN, SVM GMM and C4.5. Extensive experiments over carefully-constructed, representative datasets, evaluate these features and classifiers under different settings and compare to existing techniques. Experimental results demonstrate that SVMs with multimodal features from multi-sources are more effective at classifying video type. Finally, for answering the proposed question, results also show that automatically classifying a clip as professional-produced video or amateur-produced video can be achieved with good accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Who produced this video, amateur or professional?

Guo

Gurrin

Lao³

2013

Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our initial acceptance rate of 62.5% reflects the current state of the field: A few teams in the world produce high-quality pioneering research that supports the foundations of multimedia. We are looking forward to the presentations of the ones selected by the program committee [1,2,3,4,5]. Furthermore, we are very honored to present Koichi Shinoda (Tokyo Institute of Technology, Japan) as our keynote speaker.…”

Section: Contributions Of This Workhopmentioning

confidence: 99%

Amva'12

Friedland

Ellis

Metze

2012

Proceedings of the 20th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Media sharing sites on the Internet and the one-click upload capability of smartphones have led to a deluge of online multimedia content. Everyday, thousands of videos are uploaded into the web creating an ever-growing demand for methods to make them easier to retrieve, search, and index. While visual information is a very important part of a video, acoustic information often complements it. This is especially true for the analysis of consumer-produced, "unconstrained" videos from social media networks, such as YouTube uploads or Flickr content. The goal of the 1st ACM International Workshop on Audio and Multimedia Methods for Large-Scale Video Analysis (AMVA) is to bring together researchers and practitioners in this newly emerging field, and to foster discussion on future directions of the topic by providing a forum for focused exchanges on new ideas, developments, and results. The aim is to build a strong community and a venue that at some point can become its own conference.

show abstract

“…As the proliferation of Web 2.0 applications, user-generated video (UGV) [1] is poised to inundate the Internet. Recent statistics show that, on the primary video sharing website, YouTube 1 , 48 hours of video are uploaded every minute by users, resulting in nearly 8 years of content uploaded every day.…”

Section: Introductionmentioning

confidence: 99%

Quality Assessment of User-Generated Video Using Camera Motion

Guo

Gurrin

Hopfgartner

et al. 2013

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. With user-generated video (UGV) becoming so popular on the Web, the availability of a reliable quality assessment (QA) measure of UGV is necessary for improving the users' quality of experience in videobased application. In this paper, we explore QA of UGV based on how much irregular camera motion it contains with low-cost manner. A blockmatch based optical flow approach has been employed to extract camera motion features in UGV, based on which, irregular camera motion is calculated and automatic QA scores are given. Using a set of UGV clips from benchmarking datasets as a showcase, we observe that QA scores from the proposed automatic method and subjective method fit well. Further, the automatic method reports much better performance than the random run. These confirm the satisfaction of the automatic QA scores indicating the quality of the UGV when only considering visual camera motion. Furthermore, it also shows that the UGV quality can be assessed automatically for improving the end users quality of experience in video-based applications.

show abstract

Short user-generated videos classification using accompanied audio categories

Cited by 9 publications

References 13 publications

Who produced this video, amateur or professional?

Who produced this video, amateur or professional?

Amva'12

Quality Assessment of User-Generated Video Using Camera Motion

Contact Info

Product

Resources

About