The video first shows the difficulty of automatically finding objects in images. Subsequently, the learning process and the final result of our system AttentionMask, which uses machine learning, are shown. Learning process here refers to iteratively improving the system using manually labeled data.
To generate the video, we concatenate the results of individual images. The results (final or intermediate ones during training) are superimposed on the original image as shapes denoting the objects' location and shape predicted by the respective system.
Check our webpage for more information: https://www.inf.uni-hamburg.de/en/inst/ab/cv/pe...
This video may be embedded in other websites. You must copy the embeding code and paste it in the desired location in the HTML text of a Web page. Please always include the source and point it to lecture2go!
Please click on the link bellow and then fill out the required fields to contact our Support Team!
RRZ Support Link