Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging

04/18/2016
by   Jiren Jin, et al.
0

Automatic image annotation has been an important research topic in facilitating large scale image management and retrieval. Existing methods focus on learning image-tag correlation or correlation between tags to improve annotation accuracy. However, most of these methods evaluate their performance using top-k retrieval performance, where k is fixed. Although such setting gives convenience for comparing different methods, it is not the natural way that humans annotate images. The number of annotated tags should depend on image contents. Inspired by the recent progress in machine translation and image captioning, we propose a novel Recurrent Image Annotator (RIA) model that forms image annotation task as a sequence generation problem so that RIA can natively predict the proper length of tags according to image contents. We evaluate the proposed model on various image annotation datasets. In addition to comparing our model with existing methods using the conventional top-k evaluation measures, we also provide our model as a high quality baseline for the arbitrary length image tagging task. Moreover, the results of our experiments show that the order of tags in training phase has a great impact on the final annotation performance.

READ FULL TEXT
research
03/31/2018

Tagging like Humans: Diverse and Distinct Image Annotation

In this work we propose a new automatic image annotation model, dubbed ...
research
07/14/2011

Label-Specific Training Set Construction from Web Resource for Image Annotation

Recently many research efforts have been devoted to image annotation by ...
research
05/22/2018

COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval

This paper contributes to cross-lingual image annotation and retrieval i...
research
11/19/2017

Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement

The number of social images has exploded by the wide adoption of social ...
research
11/21/2016

Sampled Image Tagging and Retrieval Methods on User Generated Content

Traditional image tagging and retrieval algorithms have limited value as...
research
11/25/2014

Image Classification and Retrieval from User-Supplied Tags

This paper proposes direct learning of image classification from user-su...
research
06/20/2013

Analysing Word Importance for Image Annotation

Image annotation provides several keywords automatically for a given ima...

Please sign up or login with your details

Forgot password? Click here to reset