COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval
This provides a unified platform for cross-lingual image tasks, but it is incremental as it builds on existing MS-COCO data.
The authors tackled cross-lingual image annotation and retrieval by creating COCO-CN, a dataset with 20,342 images annotated with 27,218 Chinese sentences and 70,993 tags, and developed baseline methods that showed viability in experiments.
This paper contributes to cross-lingual image annotation and retrieval in terms of data and baseline methods. We propose COCO-CN, a novel dataset enriching MS-COCO with manually written Chinese sentences and tags. For more effective annotation acquisition, we develop a recommendation-assisted collective annotation system, automatically providing an annotator with several tags and sentences deemed to be relevant with respect to the pictorial content. Having 20,342 images annotated with 27,218 Chinese sentences and 70,993 tags, COCO-CN is currently the largest Chinese-English dataset that provides a unified and challenging platform for cross-lingual image tagging, captioning and retrieval. We develop conceptually simple yet effective methods per task for learning from cross-lingual resources. Extensive experiments on the three tasks justify the viability of the proposed dataset and methods. Data and code are publicly available at https://github.com/li-xirong/coco-cn