SpatialVOC2K

홈페이지 · 논문 5편

A multilingual image dataset with spatial relation annotations and object features for image-to-text generation, built using 2,026 images from the PASCAL VOC2008 dataset. Source: [SpatialVOC2K: A Multilingual Dataset of Images with Annotations and Features for Spatial Relations between Objects](/paper/spatialvoc2k-a-multilingual-dataset-of-images)