Due to multifarious data expansions that rapidly arise from user generated contents and log-data formed in internet surfing, social media 1,2,3,4,5, investigations of pathology and DNA sequence 6,7, ...
Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results