Back to Search
Start Over
COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval
- Publication Year :
- 2018
- Publisher :
- arXiv, 2018.
-
Abstract
- 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<br />Comment: accepted for publication as a regular paper in the IEEE Transactions on Multimedia
- Subjects :
- Closed captioning
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
02 engineering and technology
computer.software_genre
Annotation
0202 electrical engineering, electronic engineering, information engineering
Media Technology
Electrical and Electronic Engineering
Image retrieval
Computer Science - Computation and Language
business.industry
Computer Science Applications
Visualization
Task (computing)
Automatic image annotation
Signal Processing
Task analysis
020201 artificial intelligence & image processing
The Internet
Artificial intelligence
business
computer
Computation and Language (cs.CL)
Natural language processing
Subjects
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....a6dd1c3d49382ae134a03fe3dcf4fdea
- Full Text :
- https://doi.org/10.48550/arxiv.1805.08661