activity
20172020
most citedPointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement

53 citations · 56 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV2020

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…

cs.CV2019

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…

cs.CV201953 cited

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…

cs.CV2019

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…

cs.CV2019

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…

cs.CV20173 cited

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…