@@ -9,6 +9,10 @@ However, it is not practical in the industry-relevant applications in the contex
For example, as shown in [Fig. 1(g)](https://isrc.iscas.ac.cn/gitlab/research/locount-dataset/-/tree/master/Images/dataset-comparison.jpg), it is extremely difficult to annotate the stacked dinner plates even by a well-trained annotator.
Meanwhile, it is almost impossible for object detectors to detect all stacked dinner plates accurately, even for the state-of-the-art detectors.
Thus, it is necessary to rethink the definition of object detection in such scenarios.
In order to solve the practical industrial application problems and promote the academic research of the problem, we put forward the necessary elements of the task:
*problem definition*, *Locount dataset*, *evaluation protocol* and *baseline method*. This work was accepted by the International Artificial Intelligence Conference AAAI 2021.
