This work addresses the problem of Near-Duplicate Video Retrieval (NDVR). We propose an effective videolevel NDVR scheme based on deep metric learning that leverages Convolutional Neural Network (CNN) features from intermediate layers to generate discriminative global video representations in tandem with a Deep Metric Learning (DML) framework with two fusion variations, trained to approximate an embedding function for accurate distance calculation between two near-duplicate videos. In contrast to most state-of-the-art methods, which exploit information deriving from the same source of data for both development and evaluation (which usually results to dataset-specific solutions), the proposed model is fed during training with sampled triplets generated from an independent dataset and is thoroughly tested on the widely used CC WEB VIDEO dataset, using two popular deep CNN architectures (AlexNet, GoogleNet). We demonstrate that the proposed approach achieves outstanding performance against the state-of-the-art, either with or without access to the evaluation dataset.

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 .

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.