53 citations · 56 across the 2 of their papers we have counts for
6 papers
LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
Guohao Li, Mengmeng Xu, Silvio Giancola +2
Point cloud architecture design has become a crucial problem for 3D deep learning. Several efforts exist to manually design architectures with high accuracy in point cloud tasks su…
A Context-Aware Loss Function for Action Spotting in Soccer Videos
Anthony Cioppa, Adrien Deliège, Silvio Giancola +4
In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function tha…
PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement
Jesus Zarzar, Silvio Giancola, Bernard Ghanem
In autonomous driving pipelines, perception modules provide a visual understanding of the surrounding road scene. Among the perception tasks, vehicle detection is of paramount impo…
Leveraging Shape Completion for 3D Siamese Tracking
Silvio Giancola, Jesus Zarzar, Bernard Ghanem
Point clouds are challenging to process due to their sparsity, therefore autonomous vehicles rely more on appearance attributes than pure geometric features. However, 3D LIDAR perc…
Efficient Bird Eye View Proposals for 3D Siamese Tracking
Jesus Zarzar, Silvio Giancola, Bernard Ghanem
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 structure in point clouds impedes the use of c…
A Solution for Crime Scene Reconstruction using Time-of-Flight Cameras
Silvio Giancola, Daniele Piron, Pasquale Poppa +1
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. We used a Kinect…