Abstract | ||
---|---|---|
The problem of Near-Duplicate Video Retrieval (NDVR) has attracted increasing interest due to the huge growth of video content on the Web, which is characterized by high degree of near duplicity. This calls for efficient NDVR approaches. Motivated by the outstanding performance of Convolutional Neural Networks (CNNs) over a wide variety of computer vision problems, we leverage intermediate CNN features in a novel global video representation by means of a layer-based feature aggregation scheme. We perform extensive experiments on the widely used CC WEB VIDEO dataset, evaluating three popular deep architectures (AlexNet, VGGNet, GoogLeNet) and demonstrating that the proposed approach exhibits superior performance over the state-of-the-art, achieving a mean Average Precision (mAP) score of 0.976. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-51811-4_21 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Near-duplicate,Video retrieval,CNNs,Bag of keyframes | Computer vision,Video retrieval,Pattern recognition,Convolutional neural network,Computer science,Artificial intelligence,Feature aggregation | Conference |
Volume | ISSN | Citations |
10132 | 0302-9743 | 6 |
PageRank | References | Authors |
0.43 | 16 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Giorgos Kordopatis-Zilos | 1 | 31 | 7.38 |
Symeon Papadopoulos | 2 | 714 | 71.01 |
Ioannis Patras | 3 | 1960 | 123.15 |
Yiannis Kompatsiaris | 4 | 947 | 86.09 |