Partial Copy Detection in Videos: A Benchmark and an Evaluation of Popular Methods

Jiang, Yu‐Gang; Wang, Jiajun

doi:10.1109/tbdata.2016.2530714

Cited by 65 publications

(57 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tan et al [32] proposed a graph-based Temporal Network (TN) structure generated through keypoint frame matching, which is used for the detection of the longest shared path between two compared videos. Several recent works have employed modifications of this approach for the problem of partial-copy detection, combining it with global CNN features [17] and a CNN+RNN architecture [14]. Additionally, other approaches employ Temporal Hough Voting [8,16] to align matched frames by means of a temporal Hough transform.…”

Section: Related Workmentioning

confidence: 99%

“…However, this disregards the spatial and the temporal structure of the visual similarity, as aggregation of features is influenced by clutter and irrelevant content. Other approaches attempt to take into account the temporal sequence of frames in the similarity computation, e.g., by using Dynamic Programming [7,24], Temporal Networks [32,17] and Temporal Hough Voting [8,16]. Another line of research considers spatio-temporal video representation and matching based on Recurrent Neural Networks (RNN) [10,14] or in the Fourier domain [28,26,2].…”

Section: Introductionmentioning

confidence: 99%

“…A promising direction is exploiting better the spatial and temporal structure of videos in the similarity calculation [8,16,17]. However, recent approaches either focused on the spatial processing of frames and completely disregarded temporal information [11,21], or considered global frame representations (essentially discarding spatial information) and then considered the temporal alignment among such frame representations [7,2].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper we introduce ViSiL, a Video Similarity Learning architecture that considers fine-grained Spatio-Temporal relations between pairs of videos -such relations are typically lost in previous video retrieval approaches that embed the whole frame or even the whole video into a vector descriptor before the similarity estimation. By contrast, our Convolutional Neural Network (CNN)-based approach is trained to calculate video-to-video similarity from refined frame-to-frame similarity matrices, so as to consider both intra-and inter-frame relations. In the proposed method, pairwise frame similarity is estimated by applying Tensor Dot (TD) followed by Chamfer Similarity (CS) on regional CNN frame features -this avoids feature aggregation before the similarity calculation between frames. Subsequently, the similarity matrix between all video frames is fed to a four-layer CNN, and then summarized using Chamfer Similarity (CS) into a video-to-video similarity score -this avoids feature aggregation before the similarity calculation between videos and captures the temporal similarity patterns between matching frame sequences. We train the proposed network using a triplet loss scheme and evaluate it on five public benchmark datasets on four different video retrieval problems where we demonstrate large improvements in comparison to the state of the art. The implementation of ViSiL is publicly available 1 .

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…In the case of frame-level matching approaches, the near-duplicate videos are determined by the comparison between individual video frames or sequences. Typical frame-level approaches [48,10,32,22,54] calculate the frame-by-frame similarity and then employ sequence alignment algorithms to compute similarity at the video level. Moreover, a lot of research effort has been invested in methods that exploit spatio-temporal features to represent video segments in order to facilitate videolevel similarity computation [15,56,38,37,3].…”

Section: Frame-level Matchingmentioning

confidence: 99%

Finding Near-Duplicate Videos in Large-Scale Collections

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

Video Verification in the Fake News Era

View full text Add to dashboard Cite

This chapter discusses the problem of Near-Duplicate Video Retrieval (NDVR). The main objective of a typical NDVR approach is: given a query video, retrieve all near-duplicate videos in a video repository and rank them based on their similarity to the query. Several approaches have been introduced in the literature, which can be roughly classified in three categories based on the level of video matching, i.e. (i) video-level, (ii) frame-level and (iii) filter-and-refine matching. Two methods based on video-level matching are presented in this chapter. The first is an unsupervised scheme that relies on a modified Bag-of-Word (BoW) video representation. The second is a supervised method based on Deep Metric Learning (DML). For the development of both methods, features are extracted from the intermediate layers of Convolutional Neural Networks and leveraged as frame descriptors, since they offer a compact and informative image representation, and lead to increased system efficiency. Extensive evaluation has been conducted on publicly available benchmark datasets, and the presented methods are compared with state-of-art approaches, achieving the best results in all evaluation setups.

show abstract

“…What should the user do if he/she wants to find when such an action also happens in that cartoon? Simply finding exactly the same content using copy detection methods [12] would fail for most cases, as the content variations across videos are of great differences. As shown in the middle video of Fig.…”

Section: Introductionmentioning

confidence: 99%

Video Re-localization

Feng

Liu

et al. 2018

Computer Vision – ECCV 2018

108

View full text Add to dashboard Cite

Many methods have been developed to help people find the video contents they want efficiently. However, there are still some unsolved problems in this area. For example, given a query video and a reference video, how to accurately localize a segment in the reference video such that the segment semantically corresponds to the query video? We define a distinctively new task, namely video re-localization, to address this scenario. Video re-localization is an important emerging technology implicating many applications, such as fast seeking in videos, video copy detection, video surveillance, etc. Meanwhile, it is also a challenging research task because the visual appearance of a semantic concept in videos can have large variations. The first hurdle to clear for the video re-localization task is the lack of existing datasets. It is labor expensive to collect pairs of videos with semantic coherence or correspondence and label the corresponding segments. We first exploit and reorganize the videos in ActivityNet to form a new dataset for video re-localization research, which consists of about 10,000 videos of diverse visual appearances associated with localized boundary information. Subsequently, we propose an innovative cross gated bilinear matching model such that every time-step in the reference video is matched against the attentively weighted query video. Consequently, the prediction of the starting and ending time is formulated as a classification problem based on the matching results. Extensive experimental results show that the proposed method outperforms the competing methods. Our code is available at: https://github.com/fengyang0317/video reloc.

show abstract

Partial Copy Detection in Videos: A Benchmark and an Evaluation of Popular Methods

Cited by 65 publications

References 27 publications

ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning

ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning

Finding Near-Duplicate Videos in Large-Scale Collections

Video Re-localization

Contact Info

Product

Resources

About