publication . Conference object . Other literature type . 2017

Near-Duplicate Video Retrieval with Deep Metric Learning

Symeon Papadopoulos;
Open Access
  • Published: 23 Oct 2017
Abstract
This work addresses the problem of Near-Duplicate Video Retrieval (NDVR). We propose an effective video-level 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-sp...
Subjects
free text keywords: Near-Duplicate, Video Retrieval, Deep Metric Learning, Convolutional neural network, Feature extraction, Artificial intelligence, business.industry, business, Exploit, Computer science, Discriminative model, Convolution, Embedding, Computer vision, Pattern recognition
Funded by
EC| InVID
Project
InVID
In Video Veritas – Verification of Social Media Video Content for the News Industry
  • Funder: European Commission (EC)
  • Project Code: 687786
  • Funding stream: H2020 | IA
Download fromView all 7 versions
ZENODO
Conference object . 2017
Provider: ZENODO
Zenodo
Other literature type . 2017
Provider: Datacite
Zenodo
Other literature type . 2017
Provider: Datacite
ZENODO
Conference object . 2017
Provider: ZENODO
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Conference object . Other literature type . 2017

Near-Duplicate Video Retrieval with Deep Metric Learning

Symeon Papadopoulos;