Description
The Authoring Tools for Multimedia Content (AToMiC) Track aims to build reliable benchmarks for multimedia search systems. The focus of this track is to develop and evaluate IR techniques for text-to-image and image-to-text search problems.
Resources
| Name | Format | Description | Link |
|---|---|---|---|
| Corpus on Huggingface | Unknown | Open resource | |
| Atomic Track Home Page | Unknown | Open resource | |
| Image-to-Text relevance judgments | Unknown | qrels.2023.i2t | Open resource |
| Text-to-Image relevance judgments | Unknown | qrels.2023.t2i | Open resource |
| Image-to-Text topics | JSON | TREC-2023-Image-to-Text.json | Open resource |
| Text-to-image topics | JSON | TREC-2023-Text-to-Image.json | Open resource |