publication . Article . Other literature type . 2019

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

Vasileios Mezaris; Foteini Markatopoulou; Ioannis Patras;
Open Access
  • Published: 01 Jun 2019 Journal: IEEE Transactions on Circuits and Systems for Video Technology, volume 29, pages 1,631-1,644 (issn: 1051-8215, eissn: 1558-2205, Copyright policy)
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
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...
Persistent Identifiers
Subjects
free text keywords: Media Technology, Electrical and Electronic Engineering, video/image concept annotation, deep learning, multi-task learning, structured outputs, multi-label learning, concept correlations, video analysis, Computer science, Semantics, Annotation, Artificial intelligence, business.industry, business, Convolutional neural network, Artificial neural network, Task analysis, Data set, Linear combination, Electronic mail
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
Any information missing or wrong?Report an Issue