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

arXiv: https://arxiv.org/abs/1604.05225 · HTML: https://mlsanity.com/paper/1604.05225/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2016.

## Built on by (most cited first, 8 of 8)

- [Modeling Multi-Label Action Dependencies for Temporal Action Localization](https://mlsanity.com/paper/2103.03027/) (2021)
- [Deep Learning for Multi-Label Learning: A Comprehensive Survey](https://mlsanity.com/paper/2401.16549/) (2024)
- [AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition](https://mlsanity.com/paper/2203.05534/) (2022)
- [Tensor Normalization and Full Distribution Training](https://mlsanity.com/paper/2109.02345/) (2021)
- [Goal-driven text descriptions for images](https://mlsanity.com/paper/2108.12575/) (2021)
- [LabelKAN -- Kolmogorov-Arnold Networks for Inter-Label Learning: Avian Community Learning](https://mlsanity.com/paper/2601.18818/) (2026)
- [Visual Transformers with Primal Object Queries for Multi-Label Image Classification](https://mlsanity.com/paper/2112.05485/) (2021)
- [Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook](https://mlsanity.com/paper/2607.00839/) (2026)

## Abstract (arXiv)

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.