582 citations
- Aalto UniversityFI26 papers
- Tampere UniversityFI13 papers
- Linköping UniversitySE6 papers
- University of Eastern FinlandFI6 papers
- Helsinki Institute of PhysicsFI5 papers
- Nokia (United States)US5 papers
- University of HelsinkiFI5 papers
- University of OuluFI5 papers
- Lappeenranta-Lahti University of TechnologyFI4 papers
- Nokia (Germany)DE4 papers
- Arcada University of Applied SciencesFI3 papers
- Centre National de la Recherche ScientifiqueFR3 papers
8 papers · 1 filter
Image coding for machines: an end-to-end learned approach
Nam Le, Honglei Zhang, Francesco Cricri +2
Over recent years, deep learning-based computer vision systems have been applied to images at an ever-increasing pace, oftentimes representing the only type of consumption for thos…
Simultaneously Learning Architectures and Features of Deep Neural Networks
Tinghuai Wang, Lixin Fan, Huiling Wang
This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explic…
Fast Registration for cross-source point clouds by using weak regional affinity and pixel-wise refinement
Xiaoshui Huang, Lixin Fan, Qiang Wu +2
Many types of 3D acquisition sensors have emerged in recent years and point cloud has been widely used in many areas. Accurate and fast registration of cross-source 3D point clouds…
Object Detection in Equirectangular Panorama
Wenyan Yang, Yanlin Qian, Francesco Cricri +2
We introduced a high-resolution equirectangular panorama (360-degree, virtual reality) dataset for object detection and propose a multi-projection variant of YOLO detector. The mai…
Saliency-Enhanced Robust Visual Tracking
Caglar Aytekin, Francesco Cricri, Emre Aksu
Discrete correlation filter (DCF) based trackers have shown considerable success in visual object tracking. These trackers often make use of low to mid level features such as histo…
A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures
Xiaoshui Huang, Jian Zhang, Lixin Fan +2
We propose a systematic approach for registering cross-source point clouds. The compelling need for cross-source point cloud registration is motivated by the rapid development of a…