Dataset Groups Activity Stream COCO Captions Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect. BibTex: @dataset{Haoming_Liu_and_Yuanhe_Guo_and_Shengjie_Wang_and_Hongyi_Wen_2024, abstract = {Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect.}, author = {Haoming Liu and Yuanhe Guo and Shengjie Wang and Hongyi Wen}, doi = {10.57702/l1v13sr7}, institution = {No Organization}, keyword = {'COCO captions', 'diffusion models', 'image captioning', 'image captions', 'image-text pairs', 'object detection', 'real image style transfer', 'unpaired learning', 'vision-language pre-training', 'weak supervision'}, month = {dec}, publisher = {TIB}, title = {COCO Captions}, url = {https://service.tib.eu/ldmservice/dataset/coco-captions}, year = {2024} }
