Detecting complex events in user-generated video using concept classifiers

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

“…In this work, we still consider them as PPV. Therefore, compared with PPV, the APV has the following characteristics [7].…”

Section: Introductionmentioning

confidence: 99%

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

“…These time series recognition methods investigated are summarized in Table 1.1 [56]. Whether they utilise temporal features, the number of event/activity types and the number of concept attributes are all depicted in Max-Pooling [58] has been demonstrated to give better performance compared to other fusions for most complex events. In Max-Pooling, the maximum confidence is chosen from all keyframe images (or video subclips) for each concept to generate a fixeddimensional vector for an event or activity sample.…”

Section: Attribute-based Everyday Activity Recognitionmentioning

confidence: 99%

Computer Vision for Lifelogging

Wang

Sun

Smeaton

et al. 2018

Computer Vision for Assistive Healthcare

Self Cite

View full text Add to dashboard Cite

show abstract

“…As one of the fusion operations for concept detection results, Max-Pooling [14] has been demonstrated to give better performance compared to other fusions for most complex events. In Max-Pooling, the maximum confidence is chosen from all keyframe images (or video subclips) for each concept to generate a fixed-dimensional vector for an event or activity sample.…”

Section: Max-pooling (Mp)mentioning

confidence: 99%

What are the Limits to Time Series Based Recognition of Semantic Concepts?

Wang

Sun

Smeaton

2016

MultiMedia Modeling

View full text Add to dashboard Cite

Abstract. Most concept recognition in visual multimedia is based on relatively simple concepts, things which are present in the image or video. These usually correspond to objects which can be identified in images or individual frames. Yet there is also a need to recognise semantic concepts which have a temporal aspect corresponding to activities or complex events. These require some form of time series for recognition and also require some individual concepts to be detected so as to utilise their time-varying features, such as co-occurrence and re-occurrence patterns. While results are reported in the literature of using concept detections which are relatively specific and static, there are research questions which remain unanswered. What concept detection accuracies are satisfactory for time series recognition? Can recognition methods perform equally well across various concept detection performances? What affecting factors need to be taken into account when building concept-based high-level event/activity recognitions? In this paper, we conducted experiments to investigate these questions. Results show that though improving concept detection accuracies can enhance the recognition of time series based concepts, they do not need to be very accurate in order to characterize the dynamic evolution of time series if appropriate methods are used. Experimental results also point out the importance of concept selection for time series recognition, which is usually ignored in the current literature.

show abstract

Detecting complex events in user-generated video using concept classifiers

Abstract: Abstract

Cited by 17 publications

References 14 publications

Who produced this video, amateur or professional?

Who produced this video, amateur or professional?

Computer Vision for Lifelogging

What are the Limits to Time Series Based Recognition of Semantic Concepts?

Contact Info

Product

Resources

About