Content-Based Video Copy Detection Benchmarking at TRECVID

Awad, George; Over, Paul; Kraaij, Wessel

doi:10.1145/2629531

Cited by 28 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In watermarking-based steganography technique [21], a piece of same mark information is imbedded into multimedia content, then the watermarked multimedia content is distributed to users with multicast technology [15]. The watermark information can be copyright information, which can authenticate the owner of the multimedia content.…”

Section: Figure 4 Watermarking Scheme For Multimedia Content Protectionmentioning

confidence: 99%

See 1 more Smart Citation

Secure Multimedia Content Distribution for M2M Communication

Ye¹,

Xiong²,

Ding³

et al. 2016

IJSIA

View full text Add to dashboard Cite

show abstract

Section: Figure 4 Watermarking Scheme For Multimedia Content Protectionmentioning

confidence: 99%

“…The copy detection framework is shown in Figure (7). The detection method is based on CBCD (Content Based Copy Detection) [21]. An original feature which is registered in feature database through extracting a feature vector representing the original multimedia content.…”

Section: Figure 7 Copy Detection For Copyright Authenticationmentioning

confidence: 99%

Secure Multimedia Content Distribution for M2M Communication

Ye¹,

Xiong²,

Ding³

et al. 2016

IJSIA

View full text Add to dashboard Cite

show abstract

“…The report of those competitions concludes that current state-of-the-art methods, which are robustness focused, are not suitable for real-time applications due to their high computational cost [33]. They also reported that current methods are not focused on applications where false alarms (NOFA apps) are not tolerated nor focused on generating compact fingerprints for improving their search in databases [14, 33–35]. Also those methods, which present near perfect scores under simulated attacks in TRECVID competition, present a low performance under non-simulated or real partial-video copies (VCDB benchmark) [10].…”

Section: Related Workmentioning

confidence: 99%

Towards a Video Passive Content Fingerprinting Method for Partial-Copy Detection Robust against Non-Simulated Attacks

Guzman-Zavaleta

Feregrino-Uribe

2016

PLoS ONE

View full text Add to dashboard Cite

Passive content fingerprinting is widely used for video content identification and monitoring. However, many challenges remain unsolved especially for partial-copies detection. The main challenge is to find the right balance between the computational cost of fingerprint extraction and fingerprint dimension, without compromising detection performance against various attacks (robustness). Fast video detection performance is desirable in several modern applications, for instance, in those where video detection involves the use of large video databases or in applications requiring real-time video detection of partial copies, a process whose difficulty increases when videos suffer severe transformations. In this context, conventional fingerprinting methods are not fully suitable to cope with the attacks and transformations mentioned before, either because the robustness of these methods is not enough or because their execution time is very high, where the time bottleneck is commonly found in the fingerprint extraction and matching operations. Motivated by these issues, in this work we propose a content fingerprinting method based on the extraction of a set of independent binary global and local fingerprints. Although these features are robust against common video transformations, their combination is more discriminant against severe video transformations such as signal processing attacks, geometric transformations and temporal and spatial desynchronization. Additionally, we use an efficient multilevel filtering system accelerating the processes of fingerprint extraction and matching. This multilevel filtering system helps to rapidly identify potential similar video copies upon which the fingerprint process is carried out only, thus saving computational time. We tested with datasets of real copied videos, and the results show how our method outperforms state-of-the-art methods regarding detection scores. Furthermore, the granularity of our method makes it suitable for partial-copy detection; that is, by processing only short segments of 1 second length.

show abstract

“…Önerilen yöntem, içerik tabanlı kopya bulma probleminde yaygın olarak kullanılan TRECVID 2009 veriseti ile test edilmiştir [10]. Kullanılan test seti ve alınan sonuçlar sırasıyla Bölüm IV-A ve Bölüm IV-B'de detaylı birşekilde açıklanmıştır.…”

Section: Deneylerunclassified

“…Bu çalışmada, test seti olarak TRECVID 2009 veriseti içerisinde tanımlı olan içerik tabanlı video kopya bulma veriseti (CBCD) kullanılmıştır [10]. TRECVID 2009 CBCD veriseti 7 farklı görsel dönüşüm problemini içermektedir.…”

Section: A Test Seti Ve Ataklarunclassified

Video copy detection using motion co-occurrence feature

Arabaci

Esen

2015

2015 23nd Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

Özetçe -İçerik tabanlı video kopya bulma, özellikle telif hakkına sahip ve ticari amaçla üretilen videoların dagıtımında ve takip edilmesinde önemli bir rol oynamaktadır. Problemin çözümü için genellikle video çerçevesi içerisindeki ilgi noktalarını kullanan yerel tanımlayıcılar veya tüm çerçeve içerigini kullanan global tanımlayıcılar kullanılmaktadır. Yerel tanımlayıcılar kullanılarak elde edilen sonuçlar başarılı olmakla birlikte öznitelik çıkarma ve indeksleme işlemleri çok zaman almaktadır. Bu çalışmada, içerik tabanlı video kopya bulma problemi için hareket temelli özniteliklerden biri olan hareket birliktelik özniteligi (HBÖ) önerilmiştir. HBÖ, global bir öznitelik olmasına karşın uzamsal ve zamansal komşulugu kullanmasından dolayı içerisinde yerel bilgiyi barındırmaktadır. Aynı zamanda, video akışı içerisinde yer alan hareket bilgisinin dogrudan kullanılması ile çıkarılmaktadır. Bu sayede, öznitelik çıkarma işlemi hızlı biŗ sekilde yapılabilmektedir. Önerilen yöntemin, özellikle hareket bilgisinin korundugu ataklara karşı etkili oldugu gözlenmiştir.Anahtar Kelimeler-içerik tabanlı video kopya bulma, hareket birliktelik özniteligi.Abstract-Content-based video copy detection (CBCD) has an important role especially in distributing and tracking of copyright and commercial videos. Basically, two main descriptors are used for CBCD one of which, using the interest points in keyframes, the other using the content of a whole keyframe. Even if the local descriptor-based approaches have good results in CBCD problem, it takes too much time for extracting and indexing features. In this study, one of the motion-based features named as motion co-occurrence feature (MCF) is proposed for the solution of CBCD problem. Basically, MCF is a global feature that uses local information by considering spatial and temporal neighbourhood of motion vectors. Additionally, MCF can be extracted directly from the motion information of the video bitstream. Thus, feature extraction process can be performed quickly. The results show that the proposed method is effective especially for the attacks in which the motion information is preserved.

show abstract

Content-Based Video Copy Detection Benchmarking at TRECVID

Cited by 28 publications

References 27 publications

Secure Multimedia Content Distribution for M2M Communication

Secure Multimedia Content Distribution for M2M Communication

Towards a Video Passive Content Fingerprinting Method for Partial-Copy Detection Robust against Non-Simulated Attacks

Video copy detection using motion co-occurrence feature

Contact Info

Product

Resources

About