Publications

The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable …

We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds. Estimating 3D motions for point …

Multi-view projection methods have demonstrated promising performance on 3D understanding tasks like 3D classification and …

Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those …

Soccer broadcast video understanding has been drawing a lot of attention in recent years within data scientists and industrial …

Witchweeds (Striga spp.) and broomrapes (Orobanchaceae and Phelipanche spp.) are root parasitic plants that infest many crops in warm …

Toward the goal of automatic production for sports broadcasts, a paramount task consists in understanding the high-level semantic …

Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate …

We introduce the idea of using learnable neighbor-to-grid soft assignment in grid-based aggregation functions for the task of 3D …

Understanding videos is challenging in computer vision. In particular, the large memory footprint of an untrimmed video makes most …

Point cloud architecture design has become a crucial problem for 3D deep learning. Several efforts exist to manually design …

In autonomous driving pipelines, perception modules provide a visual understanding of the surrounding road scene. Among the perception …

In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In …

Tracking vehicles in LIDAR point clouds is a challenging task due to the sparsity of the data and the dense search space. The lack of …

Point clouds are challenging to process due to their sparsity, therefore autonomous vehicles rely more on appearance attributes than …

Despite the numerous developments in object tracking, further improvement of current tracking algorithms is limited by small and mostly …

In this paper, we introduce SoccerNet, a benchmark for action spotting in soccer videos. The dataset is composed of 500 complete soccer …

In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into …

Recent researches proved that the underbridge geometry can be reconstructed by mounting a 3D laser scanner on a motorized cart …

In this work, we propose a method for three-dimensional (3D) reconstruction of wide crime scene, based on a Simultaneous Localization and Mapping (SLAM) approach.

The aim of study was to identify whether facial features are stable in time and can be utilized for facial recognition by comparing facial images of children at different ages as well as to test the possible use of moles in recognition…

In this study, we evaluate the performances of the body tracking algorithm of the Kinect V2 low-cost time-of-flight camera for medical rehabilitation purposes…

Markerless motion capture systems have been developed in an effort to evaluate human movements in a natural setting. However, the …

A metrological characterization process for time-of-flight (TOF) cameras is proposed in this paper and applied to the Microsoft Kinect V2. Based on the Guide to the Expression of Uncertainty in Measurement (GUM), the uncertainty of a three-dimensional (3D) scene reconstruction is analysed…

This paper presents a method for measuring the non-controlled trajectory of a cart along a bounded rectilinear path. The method uses …

The paper studies how multi-camera systems can be used for registering trajectories. A sensorized tool (a paintbrush) has been used to track the movements of a painter…

The use of anthropomorphic robots for tiles decoration, painting them, links the repeatability and the high rhythm of production with a …