A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection

He, Sifeng; Yang, Xudong; Jiang, Chen; Li, Gang; Zhang, Wei; Pan, Tan; Wang, Qing; Xu, Furong; Li, Chunguang; Liu, Jingxiong; Xu, Hui; Huang, Kaiming; Cheng, Yuan; Qian, Feng; Zhang, Xiaobo; Yang, Lei

doi:10.1109/cvpr52688.2022.02041

Cited by 10 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison results are illustrated in Table 2. Specifically, to evaluate the methods, we follow the F-score metric proposed by the VCSL dataset [13], which serves as the official comparison metric of the dataset and measures the overlapped similar clips between two videos. Following [13], we choose the Temporal Network (TN) [34] as our alignment method.…”

Section: Methodsmentioning

confidence: 99%

“…Specifically, to evaluate the methods, we follow the F-score metric proposed by the VCSL dataset [13], which serves as the official comparison metric of the dataset and measures the overlapped similar clips between two videos. Following [13], we choose the Temporal Network (TN) [34] as our alignment method. We compare our method with the approaches that achieve the current state-of-the-art performance on the VCSL dataset, including ViT [8], DINO [3], R-MAC [38], ViSiL [19], and ISC [43].…”

Section: Methodsmentioning

confidence: 99%

“…The categories of videos are almost all-encompassing, including movies, TV series, commentary videos, daily videos, etc. The VCSL [13] dataset consists of more than 167,000 video infringement pairs with diverse video categories and varying video durations. Implementation Details Our DMI (feature Disentanglement and Mutual Information maximization) framework is implemented with PyTorch 1.4.0.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…The number of subfeatures is set to 𝑘 = 6. For evaluation, the widely used top-100 mAP [16] and F-score [13] metrics are adopted.…”

Section: Experimental Settingsmentioning

confidence: 99%

See 3 more Smart Citations

Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization

Liu,

Yu,

Wang

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

The self-media era provides us tremendous high quality videos. Unfortunately, frequent video copyright infringements are now seriously damaging the interests and enthusiasm of video creators. Identifying infringing videos is therefore a compelling task. Current state-of-the-art methods tend to simply feed high-dimensional mixed video features into deep neural networks and count on the networks to extract useful representations. Despite its simplicity, this paradigm heavily relies on the original entangled features and lacks constraints guaranteeing that useful task-relevant semantics are extracted from the features.In this paper, we seek to tackle the above challenges from two aspects: (1) We propose to disentangle an original high-dimensional feature into multiple sub-features, explicitly disentangling the feature into exclusive lower-dimensional components. We expect the sub-features to encode non-overlapping semantics of the original feature and remove redundant information. (2) On top of the disentangled sub-features, we further learn an auxiliary feature to enhance the sub-features. We theoretically analyzed the mutual information between the label and the disentangled features, arriving

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Experimental Settingsmentioning

confidence: 99%

“…The number of subfeatures is set to 𝑘 = 6. For evaluation, the widely used top-100 mAP [16] and F-score [13] metrics are adopted.…”

Section: Experimental Settingsmentioning

confidence: 99%

See 2 more Smart Citations

Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization

Liu,

Yu,

Wang

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…. , Xn} set of feature vectors • VGGNet [9,11,13,15,18,19,21,22] • ResNet [4,7,8,11,15] • InceptionNet [1,11,12,17] • AlexNet [1,10,12,21] Feature extraction • Fully connected layers [1,10,11,12,13,18,21] • Convolutional layers [1,4,7,8,11,12,15,17,19,22] • Low-dimensional [4,6,18,19] • RoI based features [8,22] Video matching…”

Section: Symbols Meaningmentioning

confidence: 99%

Performance Characterization of 2D CNN Features for Partial Video Copy Detection

Le,

Delalandre,

Cardot

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

2D CNN are main components for Partial Video Copy Detection (PVCD). 2D CNN features serve for the retrieval and matching of videos. Robustness is a key property of these features. It is a well-known problem in the computer vision field but little investigated for PVCD. The contributions of this paper are twofold: (i) based on a public video dataset, we provide large-scale experiments with 700 B of comparisons of 4.4 M feature vectors. We report conclusions for PVCD consistent with the state-of-the-art. (ii) the regular protocol for performance characterization is misleading for PVCD as it is bounded to the video level. A method for the characterization of key-frames with 2D CNN features is proposed. It is based on a goodness criterion and a time series modelling. It provides a fine categorization of key-frames and allows a deeper characterization of a PVCD problem with 2D CNN features.

show abstract

Learning Video Localization on Segment-Level Video Copy Detection with Transformer

Zhang,

Liu,

Zhang

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection

Cited by 10 publications

References 22 publications

Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization

Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization

Performance Characterization of 2D CNN Features for Partial Video Copy Detection

Learning Video Localization on Segment-Level Video Copy Detection with Transformer

Contact Info

Product

Resources

About