@InProceedings{Kletz2019b, author = {Sabrina Kletz and Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the 10th ACM Multimedia Systems Conference}, title = {{A comparative study of video annotation tools for scene understanding}}, year = {2019}, month = {jun}, pages = {133--144}, publisher = {ACM}, abstract = {Computers are powerful tools capable of solving a great variety of ever so complex problems, yet training them to interpret even the simplest video scenes can prove more challenging than one might imagine. Still being one of the major problems in computer vision, this issue recently is addressed by utilizing promising deep learning approaches in order to recognize objects and their semantics. For achieving this goal, huge artificial networks are fed with many human-created annotations using more or less sophisticated tools for speeding up the otherwise time-consuming task of manual annotation. Purposefully refraining from designing yet another of these annotation tools, in this work we strive for evaluating what makes existing ones great or not, i.e. we aim at determining effectiveness and efficiency of state-of-the-art object annotation tools when employed for annotating different kinds of video content. Our findings in a user study evaluating three comparable tools on three videos of distinct domains indicate a significant difference in annotation effort from a video perspective, yet no significance regarding utilized tools. Further, we determine a significant correlation between annotation time and accuracy.}, doi = {10.1145/3304109.3306223}, keywords = {Video Annotation Tools, User Study, Object Detection, Interpolation, Bounding Boxes, Machine Learning}, url = {https://dl.acm.org/citation.cfm?id=3306223} }