CroQS Benchmark
收藏资源简介：
CroQS (Cross-modal Query Suggestion) v1.0.0 is a benchmark dataset designed to evaluate methods that generate improved textual queries guided by visual results, in the context of text-to-image retrieval. The dataset supports the task of generating query suggestions grounded in visual content, specifically helping users refine or reformulate queries based on result set clusters. This version includes: 50 initial textual queries used to retrieve image sets from the MS COCO 2017 dataset. 295 manually defined semantic clusters, based on visual similarity or common properties in the image results. 8127 unique COCO images (referenced via URL, not redistributed directly). Each query result set is manually grouped into 2 to 10 clusters (average ~5.9 clusters per query). Each cluster is associated with a human-written query suggestion that describes the cluster's shared visual properties. CroQS can be used to train or evaluate models for: Query refinement and expansion Multimodal and cross-modal retrieval Cluster-based query suggestion Vision-language understanding For more details on the benchmark task and evaluation metrics, refer to our paper: Maybe You Are Looking for CroQS: Cross-modal Query Suggestion for Text-to-Image Retrieval.In Proceedings of the 46th European Conference on Information Retrieval (ECIR 2025).Springer Link | arXiv:2412.13834 Website: https://paciosoft.com/CroQS-benchmark
CroQS（Cross-modal Query Suggestion，跨模态查询建议）v1.0.0是一款基准测试数据集，专为文本到图像检索场景下，评估以视觉结果为引导生成优化文本查询的方法而设计。该数据集支持基于视觉内容的查询建议生成任务，可帮助用户基于结果集簇对查询进行优化或重构。 本版本包含以下内容： 1. 50个初始文本查询，用于从微软公共对象上下文2017数据集（MS COCO 2017）中检索图像集； 2. 295个人工定义的语义簇，基于图像结果的视觉相似性或共同属性构建； 3. 8127张独特的COCO图像（仅通过URL引用，未直接进行重新分发）； 4. 每个查询的结果集均被手动划分为2至10个簇（平均每个查询约包含5.9个簇）； 5. 每个簇均关联一条人工撰写的查询建议，用于描述该簇共享的视觉属性。 CroQS可用于训练或评估面向以下任务的模型： - 查询优化与扩展 - 多模态与跨模态检索 - 基于簇的查询建议 - 视觉语言理解 如需了解该基准任务与评估指标的更多细节，请参阅我们的论文：《Maybe You Are Looking for CroQS: Cross-modal Query Suggestion for Text-to-Image Retrieval》，发表于第46届欧洲信息检索大会（ECIR 2025）。Springer Link | arXiv:2412.13834 数据集官网：https://paciosoft.com/CroQS-benchmark
