SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09625 · ECCV · 2022

Explicit Image Caption Editing

Zhen Wang, Yulei Niu, Long Chen, Guangxing Han, Jun Xiao, Jian Shao, Wenbo Ma

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption. However, all existing caption editing works are implicit models, i.e., they directly produce the refined captions without explicit connections to the reference captions. In this paper, we introduce a new task: Explicit Caption Editing (ECE). ECE models explicitly generate a sequence of edit operations, and this edit operation sequence can translate the reference caption into a refined one. Compared to the implicit editing, ECE has multiple advantages: 1) Explainable: it can trace the whole editing path. 2) Editing Efficient: it only needs to modify a few words. 3) Human-like: it resembles the way that humans perform caption editing, and tries to keep original sentence structures. To solve this task, we propose the first ECE model: TIger. It is a non-autoregressive transformerbased model, consisting of three modules: Tagger del , Tagger add , and Inserter. Specifically, Tagger del decides whether each word should be preserved or not, Tagger add decides where to add new words, and Inserter predicts the specific word for adding. To further facilitate ECE research, we propose two ECE benchmarks by re-organizing two existing datasets, dubbed COCO-EE and Flickr30K-EE, respectively. Extensive ablations on both two benchmarks have demonstrated the effectiveness of TIger.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.09625")
get_code_for_paper("2207.09625")
have("2207.09625")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.09625.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.09625.svg)](https://syntology.ai/paper/2207.09625)

Connect an agent — have() is free.