Microsoft COCO

doi:doi:10.57702/0uc30wes

Microsoft COCO

The Microsoft COCO dataset was used for training and evaluating the CNNs because it has become a standard benchmark for testing algorithms aimed at scene understanding and pixel-wise segmentation, and it also provides a rich array of relatively context-free images.

BibTex:

@dataset{Tsung-Yi_Lin_and_Michael_Maire_and_Serge_Belongie_and_James_Hays_and_Pietro_Perona_and_Deva_Ramanan_and_Piotr_Dollár_and_C_Lawrence_Zitnick_2024,
    abstract = {The Microsoft COCO dataset was used for training and evaluating the CNNs because it has become a standard benchmark for testing algorithms aimed at scene understanding and pixel-wise segmentation, and it also provides a rich array of relatively context-free images.},
    author = {Tsung-Yi Lin and Michael Maire and Serge Belongie and James Hays and Pietro Perona and Deva Ramanan and Piotr Dollár and C Lawrence Zitnick},
    doi = {10.57702/0uc30wes},
    institution = {No Organization},
    keyword = {'COCO', 'Image Annotation', 'Image Captioning', 'Image Classification', 'Image Recognition', 'Image Segmentation', 'Image Understanding', 'Image captioning', 'Image classification', 'Image recognition', 'Instance Segmentation', 'Large-Scale Dataset', 'Large-scale datasets', 'MS-COCO dataset', 'Multi-label Recognition', 'Natural Scenes', 'Object Detection', 'Object Segmentation', 'Object detection', 'Semantic Segmentation', 'Semantic segmentation', 'Visual Question Answering', 'Visual Recognition', 'bounding box regression', 'bounding boxes', 'coco', 'computer vision', 'image annotation', 'image captioning', 'image classification', 'image datasets', 'image harmonization', 'image retrieval', 'image segmentation', 'instance segmentation', 'large scale', 'low-quality examples', 'masks', 'multimodal matching', 'object detection', 'visual recognition'},
    month = {nov},
    publisher = {TIB},
    title = {Microsoft COCO},
    url = {https://service.tib.eu/ldmservice/dataset/microsoft-coco},
    year = {2024}
}