This paper presents a platform that aims at monitoring and analyzing large service-oriented applications executing on a very large scale. This is part of a vision of web-scale service utilization and management that is proposed by the SOA4All EU project. The paper shows how the platform obtains data from distributed runtimes and how it presents monitoring information at different levels of abstraction. They range from low-level infrastructure-related event details to high-level service and process analysis. Each level uses appropriate visualization techniques and widgets in order to convey the relevant information to the users in an efficient manner. The platform is under development and an advanced prototype is already available and described in the paper.

Literature on self-assessment in machine learning mainly focuses on the production of well-calibrated algorithms through consensus frameworks i.e. calibration is seen as a problem. Yet, we observe that learning to be properly confident could behave like a powerful regularization and thus, could be an opportunity to improve performance.Precisely, we show that used within a framework of action detection, the learning of a self-assessment score is able to improve the whole action localization process. Experimental results show that our approach outperforms the state-of-the-art on two action detection benchmarks. On THUMOS14 dataset, the mAP at tIoU @0.5 is improved from 42.8% to 44.6%, and from 50.4% to 51.7% on Activ-ityNet1.3 dataset. For lower tIoU values, we achieve even more significant improvements on both datasets.

Action spotting has recently been proposed as an alternative to action detection and key frame extraction. However, the current state-of-the-art method of action spotting requires an expensive ground truth composed of the search sequences employed by human annotators spotting actions -a critical limitation.In this article, we propose to use a reinforcement learning algorithm to perform efficient action spotting using only the temporal segments from the action detection annotations, thus opening an interesting solution for video understanding.Experiments performed on THUMOS14 and ActivityNet datasets show that the proposed method, named ActionSpotter, leads to good results and outperforms state-of-the-art detection outputs redrawn for this application. In particular, the spotting mean Average Precision on THUMOS14 is significantly improved from 59.7% to 65.6% while skipping 23% of video.

No abstract