Sport Type Classification of Mobile Videos

Cricri, Francesco; Roininen, Mikko J.; Leppänen, Jussi; Mate, Sujeet; Curcio, Igor D. D.; Uhlmann, Stefan; Gabbouj, Moncef

doi:10.1109/tmm.2014.2307552

Cited by 30 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. (2014) [14].A comparative analysis was done using fuses of modalities separately for each class between multi-class SVM and a modified version of multi-class SVM. In several cases another 2D majority voting technique is introduced to achieve the highest event-level accuracy.…”

Section: Related Workmentioning

confidence: 99%

Automatic Video Classification: A Review

Rani¹,

Kaur²,

Kaswan³

2020

EAI Endorsed Transactions on Creative Technologies

View full text Add to dashboard Cite

INTRODUCTION: In last few years number of internet users and available bandwidth has been increased exponentially. The availability of internet with such a low cost is making audiovisual content a more popular and easier form of information exchange. The internet is having a huge amount of this audiovisual content and to classify and choose a particular type of video is becoming a difficult task. A number of video classification methods (like text, audio and video feature extraction) have been proposed by researcher's community OBJECTIVES: This work is carried out to give a review of different video classification techniques and give a comparative analysis of available video classification techniques and to suggest the most accurate and efficient method of video classification. METHODS: Text, Audio and Visual video classification techniques. RESULTS: It has been observed that a combination of audio and visual feature extraction can provide better results. CONCLUSION: There are various methods of video classification either by using text, audio or video extraction. The text feature extraction is the least used method of video classification. The audio and visual feature extraction is being used in various applications but as we can understand that both the audio and visual feature extractions are having equal importance in video feature extraction but if we use combination of both these approaches, the results in form of accuracy of video classification can be further improved.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Video Classification: A Review

Rani¹,

Kaur²,

Kaswan³

2020

EAI Endorsed Transactions on Creative Technologies

View full text Add to dashboard Cite

show abstract

“…CriCri [3] shows a first step towards replacing video analysis with mechanisms, that leverage different sensors in the recording devices to compose the video. Without respecting visual features the resulting quality of such approaches degrades [4] but the speed increases.…”

Section: Background and Related Workmentioning

confidence: 99%

Video composition by the crowd

Wilk

Kopf

Effelsberg

2015

Proceedings of the 6th ACM Multimedia Systems Conference

View full text Add to dashboard Cite

To compose high-quality movies directors need life-long learning and talent. User-generated video defines a new era of video production in which non-professionals record videos and share them on platforms such as YouTube. As hiring professional directors results in high costs, our work focuses on replacing those directors by crowdsourcing. The proposed system allows users to record and stream live videos to servers on which workers create a video mashup. A smartphone application for recording live video has been designed that supports the composition in the crowd by a multi-modal analysis of the recording quality. The contributions of this work are: The proposed system demonstrates that composing a large number of video views can be achieved in near real-time. Second, the system achieves comparable video quality for user-generated video in comparison to manual composition. Third, it offers insights on how to design realtime capable crowdsourcing systems. Fourth, by leveraging multi-modal features that can already be evaluated during recording the number of streams considered for presentation can be reduced.

show abstract

“…As a step after static image, studies on video has attracted more and more researchers' attention in computer vision community in recent years. Lately, researches like object tracking [1][2][3], gait recognition [4,5] and activity recognition [6][7][8] achieved competitive results and all have promising future.…”

Section: Introductionmentioning

confidence: 99%

AED-Net: An Abnormal Event Detection Network

et al. 2019

View full text Add to dashboard Cite

It is challenging to detect the anomaly in crowded scenes for quite a long time. In this paper, a selfsupervised framework, abnormal event detection network (AED-Net), which is composed of PCAnet and kernel principal component analysis (kPCA), is proposed to address this problem. Using surveillance video sequences of different scenes as raw data, PCAnet is trained to extract high-level semantics of crowd's situation. Next, kPCA, a oneclass classifier, is trained to determine anomaly of the scene. In contrast to some prevailing deep learning methods, the framework is completely self-supervised because it utilizes only video sequences in a normal situation. Experiments of global and local abnormal event detection are carried out on UMN and UCSD datasets, and competitive results with higher EER and AUC compared to other state-of-the-art methods are observed. Furthermore, by adding local response normalization (LRN) layer, we propose an improvement to original AED-Net. And it is proved to perform better by promoting the framework's generalization capacity according to the experiments.

show abstract

Sport Type Classification of Mobile Videos

Cited by 30 publications

References 16 publications

Automatic Video Classification: A Review

Automatic Video Classification: A Review

Video composition by the crowd

AED-Net: An Abnormal Event Detection Network

Contact Info

Product

Resources

About