Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a challenging problem. In this article, we focus on the recently introduced text-motion retrieval tasks, which aim to search for database motions that are the most relevant to a specified natural language textual description ( text-to-motion ) and vice-versa ( motion-to-text ). Despite recent efforts to explore these promising avenues, a primary challenge remains the insufficient data available to train robust text-motion models effectively. To address this issue, we propose to investigate joint-dataset learning—where we train on multiple text-motion datasets simultaneously—together with the introduction of a Cross-Consistent Contrastive Loss (CCCL) function, which regularizes the learned text-motion common space by imposing uni-modal constraints that augment the representation ability of the trained network. To learn a proper motion representation, we also introduce a transformer-based motion encoder, called MoT++, which employs spatio-temporal attention to process skeleton data sequences. We demonstrate the benefits of the proposed approaches on the widely used KIT Motion Language and HumanML3D datasets, including also some results on the recent Motion-X dataset. We perform detailed experimentation on joint-dataset learning and cross-dataset scenarios, showing the effectiveness of each introduced module in a carefully conducted ablation study and, in turn, pointing out the limitations of state-of-the-art methods. The code for reproducing our results is available here: https://github.com/mesnico/MOTpp .

Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available here: https://github.com/mesnico/text-to-motion-retrieval.

The purpose of this paper is to introduce and describe a new Ruby benchmarking tool.We will describe the background of Ruby benchmarking and the advantages of the new tool.The paper documents the benchmarking process as well as methods used to obtain results and run tests.To illustrate the provided tool, results that were obtained by running a developed benchmarking tool on existing and available official ruby benchmarks are provided.These results document advantages in using various Ruby compilers or Ruby implementations.

Cyber attacks have become ubiquitous and in order to face current threats it is important to understand them. Studying attacks in a real environment however, is not viable and therefore it is necessary to find other methods how to examine the nature of attacks. Gaining detailed knowledge about them facilitates designing of new detection methods as well as understanding their impact. In this paper we present a testbed framework to simulate attacks that enables to study a wide range of security scenarios. The framework provides a notion of real-world arrangements, yet it retains full control over all the activities performed within the simulated infrastructures. Utilizing the sandbox environment, it is possible to simulate various security attacks and evaluate their impacts on real infrastructures. The design of the framework benefits from IaaS clouds. Therefore its deployment does not require dedicated facilities and the testbed can be deployed over miscellaneous contemporary clouds. The viability of the testbed has been verified by a simulation of particular DDoS attack.