CLEVR

doi:doi:10.57702/pyf82r40

CLEVR

CLEVR images contain objects characterized by a set of attributes (shape, color, size and material). The questions are grouped into 5 categories: Exist, Count, CompareInteger, CompareAttribute, QueryAttribute.

BibTex:

@dataset{Justin_Johnson_and_Bharath_Hariharan_and_Laurens_van_der_Maaten_and_Li_Fei-Fei_and_C_Lawrence_Zitnick_and_Ross_Girshick_2024,
    abstract = {CLEVR images contain objects characterized by a set of attributes (shape, color, size and material). The questions are grouped into 5 categories: Exist, Count, CompareInteger, CompareAttribute, QueryAttribute.},
    author = {Justin Johnson and Bharath Hariharan and Laurens van der Maaten and Li Fei-Fei and C Lawrence Zitnick and Ross Girshick},
    doi = {10.57702/pyf82r40},
    institution = {No Organization},
    keyword = {'3D objects', 'Attention', 'CLEVR', 'Compositional Language', 'Diagnosis', 'Elementary Visual Reasoning', 'Image Question Answering', 'Image Understanding', 'Object Segmentation', 'Question Answering', 'Soft-argmax', 'VQA', 'Visual Question Answering', 'Visual Reasoning', 'attributes', 'compositional language', 'compositional zero-shot learning', 'discrete reasoning', 'elementary visual reasoning', 'functional program annotations', 'gray photo backdrop', 'image reasoning', 'object categories', 'primitive shapes', 'question answering', 'relational questions', 'scene graph', 'synthetic dataset', 'visual question answering'},
    month = {dec},
    publisher = {TIB},
    title = {CLEVR},
    url = {https://service.tib.eu/ldmservice/dataset/clevr},
    year = {2024}
}