4 datasets found

Flickr8K dataset is a collection of 8,000 images with 5 sentences describing each image content

Generating natural language descriptions for images is a challenging task. The traditional way is to use the convolutional neural network (CNN) to extract image features,...

Human pose estimation refers to the task of recognizing postures by localizing body keypoints (head, shoulders, elbows, wrists, knees, ankles, etc.) from images.

Real estate appraisal dataset with structured data of 32,700 real estates from Asheville, NC, and satellite images from Bing Maps.