International audience

We present a data-driven framework for unsupervised human motion retargeting that animates a target subject with the motion of a source subject. Our method is correspondence-free, requiring neither spatial correspondences between the source and target shapes nor temporal correspondences between different frames of the source motion. This allows to animate a target shape with arbitrary sequences of humans in motion, possibly captured using $4 D$ acquisition platforms or consumer devices. Our method unifies the advantages of two existing lines of work, namely skeletal motion retargeting, which leverages long-term temporal context, and surface-based retargeting, which preserves surface details, by combining a geometry-aware deformation model with a skeleton-aware motion transfer approach. This allows to take into account long-term temporal context while accounting for surface details. During inference, our method runs online, i.e. input can be processed in a serial way, and retargeting is performed in a single forward pass per frame. Experiments show that including long-term temporal context during training improves the method’s accuracy for skeletal motion and detail preservation. Furthermore, our method generalizes to unobserved motions and body shapes. We demonstrate that our method achieves state-of-the-art results on two test datasets and that it can be used to animate human models with the output of a multi-view acquisition platform. Code is available at https://gitlab.inria.fr/rrekikdi/humanmotion-retargeting2023.

Abstract Generating realistic animated virtual humans is a problem that has been extensively studied with many applications in different types of virtual environments. However, the creation process of such realistic animations is challenging, especially because of the number and variety of influencing factors, that should then be identified and evaluated. In this paper, we attempt to provide a clearer understanding of how the multiple factors that have been studied in the literature impact the level of realism of animated virtual humans, by providing a survey of studies assessing their realism. This includes a review of features that have been manipulated to increase the realism of virtual humans, as well as evaluation approaches that have been developed. As the challenges of evaluating animated virtual humans in a way that agrees with human perception are still active research problems, this survey further identifies important open problems and directions for future research.

Assessing E-commerce web sites quality is essential not only to have recommendations for improvement but also to make comparisons with competitors. In this paper, the aim is to know the best criteria for the evaluation and obtain a weight for them using fuzzy Analytic Network Process (fuzzy ANP). The subjective judgments of the decision maker are expressed by fuzzy numbers. The decision making problem is solved by making fuzzy pairwise comparisons and a feedback between the criteria.

Multiple Criteria Decision Making (MCDM) is widely used in everyday life especially to make decisions between conflicted criteria. In this paper, MCDM is explored in the Web domain that plays a major role in the modern society. A web site can provide or not users' needs. Assess the quality of web sites requires a list of criteria and sub-criteria, they depend also on web site category. So, to qualify criteria versus others it is important to resort to Multi-Criteria decision Making method. Weighing criteria, ranking web sites or other purposes of assessment can be resolved by MCDM. This paper identifies and discusses some methods and techniques in this area; it proposes also a comparative study between them and concludes with some findings discussions and future issues.

The amount of circulating data on the internet has witnessed a considerable increase during the last decades. A web site is the main source that provides users' needs. However, some of the existing web sites are not well intentioned by users. Many studies have treated the problem of assessing the web sites' quality of different categories such as ecommerce, education, entertainment, health, etc. The problematic implies a multiple criteria decision making (MCDM) due to the multiple conflicting criteria for assessment. Existing methods are mainly based on making a hierarchy to divide high level criteria, sub-level criteria and alternatives. There is no standard until now that defines important criteria for evaluation. Indeed, this paper presents a process of collecting and extracting data from a list of studies according to a Systematic Literature Review (SLR) method. In fact, it is necessary to know frequent criteria used in the literature for establishing the task of assessment. This paper proposes also a determination of an association rules' set extracted from a set of criteria by applying an Apriori method.