publication . Article . Other literature type . 2019

Implicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation

Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis;
Open Access
  • Published: 01 Jun 2019
Abstract
In this paper, we propose a deep convolutional neural network (DCNN) architecture that addresses the problem of video/image concept annotation by exploiting concept relations at two different levels. At the first level, we build on ideas from multi-task learning, and propose an approach to learn concept-specific representations that are sparse, linear combinations of representations of latent concepts. By enforcing the sharing of the latent concept representations, we exploit the implicit relations between the target concepts. At a second level, we build on ideas from structured output learning and propose the introduction, at training time, of a new cost term t...
Subjects
free text keywords: video/image concept annotation, deep learning, multi-task learning, structured outputs, multi-label learning, concept correlations, video analysis, Media Technology, Electrical and Electronic Engineering, Pattern recognition, Task analysis, Annotation, Artificial neural network, Data set, Semantics, Artificial intelligence, business.industry, business, Automatic image annotation, Convolutional neural network, Linear combination, Computer science
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
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Article . Other literature type . 2019

Implicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation

Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis;